浏览全部资源
扫码关注微信
网络出版日期： 2024-10-16 ，
移动端阅览
刘草,曹婷,康文雄等.基于深度学习的单视图三维物体重建研究综述[J].中国图象图形学报,
Liu Cao,Cao Ting,Kang Wenxiong,et al.Single-view 3D object reconstruction based on deep learning： A survey[J].Journal of Image and Graphics,
从单个视图恢复物体三维结构信息是计算机视觉领域的重要课题，在工业生产、医疗诊断、虚拟现实等领域发挥重要作用。传统单视图三维物体重建方法需要结合几何模板和几何假设以完成特定场景对象的三维重建任务。而当前基于深度学习的单视图三维物体重建方法通过数据驱动的方式，在重建对象适用范围和重建模型鲁棒性等方面取得进展。本文首先讨论近年来单视图三维物体重建领域常用的数据集与评价指标。然后围绕基于深度学习的单视图三维物体重建领域，对有监督学习单视图三维物体重建、无监督学习单视图三维物体重建和半监督学习单视图三维物体重建等相关研究工作进行系统性的分析和总结。最后，对基于深度学习的单视图三维物体重建方法未解决难题进行总结，并展望未来可能的发展趋势与关键技术。
Single-view 3D （Three-dimensional） object reconstruction seeks to leverage the 2D （Two-dimensional） structure of a single-view image to reconstruct the 3D shape of an object， facilitating subsequent tasks such as 3D object detection， 3D object recognition and 3D semantic segmentation. In recent years， single-view 3D object reconstruction has emerged as a pivotal topic in computer vision， with wide-ranging applications in industrial production， medical diagnostics， virtual reality， and other fields. The traditional single-view 3D object reconstruction methods rely on a combination of geometric templates and geometric assumptions to complete the 3D reconstruction task of specific scene objects. However， the traditional methods based on geometric templates are tailored to specific objects， limiting their generality and scalability. The traditional methods based on geometric assumptions require strong prior conditions for the object， which limits the reconstruction quality of different changing scenes. The current single-view 3D object reconstruction methods based on deep learning have made significant progress in terms of the applicability of reconstructed objects and the robustness of reconstructed models through data-driven approaches. To further understand the current development of single-view 3D object reconstruction methods based on deep learning， this paper systematically analyzes and summarizes three aspects： commonly used datasets and evaluation indicators， method classification and improvement innovation， problem challenges， and development trends in the field of single-view 3D object reconstruction.This paper first focuses on the commonly used datasets and evaluation indicators in the field of single-view 3D object reconstruction. The datasets is the foundation of 3D reconstruction methods based on deep learning and can be divided into three categories： RGBD （Red-Green-Blue-Depth） datasets， synthetic datasets， and real scene datasets. The RGBD datasets contain object depth information， which is commonly used for algorithm testing and evaluation； The synthetic datasets contain large-scale rendering object images and 3D shape data， which are commonly used for algorithm training and evaluation； The real scene datasets contain a limited number of real object images and 3D shape， which are commonly used for algorithm evaluation. The evaluation indicators can quantitatively demonstrate algorithm performance， mainly including distance evaluation indicators and classification evaluation indicators. The distance evaluation indicators are mainly used to evaluate the shape distance between the reconstructed 3D model and the ground truth 3D model. The smaller the value， the closer the overall shape of the reconstructed 3D model is to the ground truth 3D model. The classification evaluation indicators are mainly used to evaluate the accuracy of the 3D shape classification of each point in the 3D space. The larger the value， the more accurate the reconstructed 3D model will be.Then this paper analyzes the field of single-view 3D object reconstruction based on deep learning and systematically summarizes the research work related to supervised learning single-view 3D object reconstruction， unsupervised learning single-view 3D object reconstruction， and semi-supervised learning single-view 3D object reconstruction. The supervised learning single view 3D object reconstruction methods mainly focus on the issue of reconstruction resolution in the early stage. With the improvement of 3D representations， especially the application of implicit 3D representation， high-resolution reconstruction of object details has become possible； Subsequent works improve and innovate various aspects such as input image， encoding and decoding， prior knowledge， and general structure to further solve reconstruction problems such as unknown perspectives， key details， and generalized shapes. The unsupervised learning single view 3D object reconstruction methods mainly focus on improving the rendering process in the early stage， laying the foundation for unsupervised learning. Subsequent works improve and innovate from the perspectives of rendering image quantity， image feature attributes， and additional prior knowledge， which can further solve the problems of lighting interference， background interference， and so on. The semi-supervised learning single view 3D object reconstruction methods are mainly divided into 2D labeled data-based methods and 3D labeled data-based methods. The former proposes a small sample data training paradigm and a general data training paradigm to overcome challenges such as difficulty in 3D annotation， deviation， and inconsistency between annotation data and test data； The latter enhances the robust generalization performance of reconstruction through semantic and perspective information. The above three learning methods have their own advantages and disadvantages in terms of technical frameworks. Supervised learning methods utilize 3D labeled data for learning and reconstruction， resulting in high reconstruction quality， but are limited by the high cost of data annotation； Unsupervised learning methods can directly use 2D images to learn and reconstruct， effectively reducing training costs， but the reconstruction quality is not stable enough； The semi-supervised learning methods propose a paradigm for joint learning of labeled and unlabeled data to address the problems of high data annotation cost and unstable reconstruction quality， which combine the advantages of the two methods mentioned above and have been widely studied.In addition， this paper summarizes the unresolved challenges from the perspectives of data， training paradigms， evaluation metrics， and reconstruction performance； Proposes possible future development trends and key technologies of single-view 3D object reconstruction methods based on deep learning. For the difficult data collection problem of wild objects， it is necessary to study how to use the Internet object image data to build datasets and develop efficient interactive annotation tools， which can reduce data collection costs and annotation costs. For the insufficient learning problem of local object structures， it is necessary to study the training paradigm guided by prior knowledge of local object structures， which can enhance the accuracy and reliability of single-view 3D object reconstruction. For the limited reconstruction performance problem of few-shot 3D annotated data， it is necessary to design the optimal combination of different tasks and develop multi-task learning methods， which can obtain more effective semantic information of objects and supplement effective object reconstruction supervision information； For the neglected local structure assessment problem of the exiting evaluation indicators， it is necessary to design reconstruction evaluation indicators that focus on the reconstruction results of local structures， which can further guide high-precision reconstruction optimization； For the long training optimization cycles and limited objects categories problem of the existing methods， it is necessary to study 3D foundation models that achieve universal category object shape reconstruction， which can promote the development and application of single view 3D object reconstruction methods.
深度学习三维物体重建单视图有监督学习无监督学习半监督学习
deep learning3D object reconstructionsingle-viewsupervised learningunsupervised learningsemi-supervised learning
Alsadoon A， AlSallami N， Rashid T A， Gosper J J， Prasad P W C and Haddad S. 2024. DVT： a recent review and a taxonomy for oral and maxillofacial visualization and tracking based augmented reality： image guided surgery. Multimedia tools and applications， 83（1）： 685-729 ［ DOI：10.1007/s11042-023-15581-w］
Alwala K V， Gupta A and Tulsiani S. 2022. Pretrain， Self-train， Distill： A simple recipe for Supersizing 3D Reconstruction//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. New Orleans， LA， USA， IEEE.： 3763-3772 ［ DOI：10.1109/CVPR52688.2022.00375http://dx.doi.org/10.1109/CVPR52688.2022.00375］
Aygun M and Mac Aodha O. 2024. SAOR： Single-View Articulated Object Reconstruction// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle，WA， USA. IEEE. 10382-10391 ［ DOI： 10.48550/arXiv.2303.13514http://dx.doi.org/10.48550/arXiv.2303.13514］
Bai J， Meng Q L， Xu H and Yang Z Y. 2022. ST-Rec3D： structure and target-awarea 3D reconstruction. Journal of Graphics， 43（3）： 469-477.
白静， 孟庆亮， 徐昊， 范有福， 杨瞻源. 2022. ST-Rec3D：基于结构和目标感知的三维重建. 图学学报， 43（3）： 469-477 ［ DOI：10.11996/JG.j.2095-302X.2022030469］
Bednarik J， Fua P and Salzmann M. 2018. Learning to Reconstruct Texture-Less Deformable Surfaces from a Single View//Proceedings of the International Conference on 3D Vision （3DV）. Verona， Italy， IEEE. 606-615 ［ DOI：10.1109/3DV.2018.00075http://dx.doi.org/10.1109/3DV.2018.00075］
Kerbl B， Kopanas G， Leimkuehler T and Drettakis G. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Trans. Graph.， 42（4）： ［ DOI：10.1145/3592433］
Chabra R， Lenssen J E， Ilg E， Schmidt T， Straub J， Lovegrove S and Newcombe R. 2020. Deep Local Shapes： Learning Local SDF Priors for Detailed 3D Reconstruction //Proceedings of the European Conference on Computer Vision （ECCV）. Glasgow， UK， Springer. 608-625 ［ DOI：10.48550/arXiv.2003.10983http://dx.doi.org/10.48550/arXiv.2003.10983］
Chang A X， Funkhouser T， Guibas L， Hanrahan P， Huang Q， Li Z， Savarese S， Savva M， Song S， Su H， Xiao J， Yi L and Yu F. ShapeNet： An Information-Rich 3D Model Repository ［EB/OL］.［2015-12-09］. https://arxiv.org/pdf/1512.03012.pdfhttps://arxiv.org/pdf/1512.03012.pdf
Charles R Q， Su H， Kaichun M and Guibas L J. 2017. PointNet： Deep Learning on Point Sets for 3D Classification and Segmentation //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Honolulu， HI， USA， IEEE. 77-85 ［ DOI： 10.1109/CVPR.2017.16http://dx.doi.org/10.1109/CVPR.2017.16］
Chen R， Yin M， Shen J and Ma W. 2024. Recon3D： High Quality 3D Reconstruction from a Single Image Using Generated Back-View Explicit Priors//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle，WA， USA. IEEE. 2802-2811 ［ DOI］
Chen W， Qian S， Fan D， Kojima N， Hamilton M and Deng J. 2020a. OASIS： A Large-Scale Dataset for Single Image 3D in the Wild //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 676-685 ［ DOI：10.1109/CVPR42600.2020.00076http://dx.doi.org/10.1109/CVPR42600.2020.00076］
Chen W， Gao J， Ling H， Smith E J， Lehtinen J， Jacobson A and Fidler S. 2020b. Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer［C］ //Proceedings of the Advances in Neural Information Processing Systems （NIPS）. Red Hook， NY， USA， Inc. 9577-9587 ［ DOI：10.48550/arXiv.1908.01210http://dx.doi.org/10.48550/arXiv.1908.01210］
Chen Z and Zhang H. 2019b. Learning Implicit Fields for Generative Shape Modeling //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Long Beach， CA， USA， IEEE. 5932-5941 ［ DOI：10.1109/CVPR.2019.00609http://dx.doi.org/10.1109/CVPR.2019.00609］
Choy C B， Xu D， Gwak J， Chen K and Savarese S. 2016. 3D-R2N2： A Unified Approach for Single and Multi-view 3D Object Reconstruction //Proceedings of the European Conference on Computer Vision （ECCV）， Glasgow， UK， Springer.628-644 ［ DOI：10.48550/arXiv.1604.00449http://dx.doi.org/10.48550/arXiv.1604.00449］
Chung J， Oh J and Lee K M. 2024. Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 811-820 ［ DOI：10.48550/arXiv.2311.13398http://dx.doi.org/10.48550/arXiv.2311.13398］
Dai A， Chang A X， Savva M， Halber M， Funkhouser T and Nießner M. 2017. ScanNet： Richly-Annotated 3D Reconstructions of Indoor Scenes //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Honolulu， HI， USA， IEEE. 2432-2443 ［ DOI：10.1109/CVPR.2017.261http://dx.doi.org/10.1109/CVPR.2017.261］
Duggal S and Pathak D. 2022. Topologically- Aware Deformation Fields for Single-View 3D Reconstruction //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. New Orleans， LA， USA， IEEE. 1526-1536 ［ DOI：10.1109/CVPR52688.2022.00159http://dx.doi.org/10.1109/CVPR52688.2022.00159］
Dundar A， Gao J， Tao A and Catanzaro B. 2023. Fine Detailed Texture Learning for 3D Meshes With Generative Models. IEEE Transactions on Pattern Analysis and Machine Intelligence， 45（12）： 14563-14574 ［ DOI：10.1109/TPAMI.2023.3319429］
Elich C， Oswald M R， Pollefeys M and Stuckler J. Semi-Supervised Learning of Multi-Object 3D Scene Representations ［EB/OL］. ［2021-04-20］. https://arxiv.org/pdf/2010.04030.pdfhttps://arxiv.org/pdf/2010.04030.pdf
Fahim G， Amin K and Zarif S. 2021. Single-View 3D reconstruction： A Survey of deep learning methods. Computers & graphics， 94（Feb.）： 164-190 ［ DOI：10.1016/j.cag.2020.12.004］
Fang Q， Shuai Q， Dong J， Bao H and Zhou X. 2021. Reconstructing 3D Human Pose by Watching Humans in the Mirror //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， TN， USA， IEEE. 12809-12818 ［ DOI：10.1109/CVPR46437.2021.01262http://dx.doi.org/10.1109/CVPR46437.2021.01262］
Gan Y S， Chen W， Yau W， Zou Z， Liong S and Wang S. 2023. 3D SOC-Net： Deep 3D reconstruction network based on self-organizing clustering mapping. Expert Syst. Appl.， 213（PC）： ［ DOI：10.1016/j.eswa.2022.119209http://dx.doi.org/10.1016/j.eswa.2022.119209］
Gao Z， Zhang J， Guo Y， Ma C， Zhai G and Yang X. 2020. Semi-supervised 3D Face Representation Learning from Unconstrained Photo Collections //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops （CVPRW）. Seattle， WA， USA， IEEE. 1426-1435 ［ DOI：10.1109/CVPRW50498.2020.00182http://dx.doi.org/10.1109/CVPRW50498.2020.00182］
Geiger A， Lenz P， Stiller C and Urtasun R. 2013. Vision meets robotics： The KITTI dataset. The International Journal of Robotics Research， 32（11）： 1231-1237 ［ DOI：10.1177/0278364913491297］
Groueix T， Fisher M， Kim V G， Russell B C and Aubry M. 2018. A Papier-Mache Approach to Learning 3D Surface Generation //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， UT， USA， IEEE. 216-224 ［ DOI：10.1109/CVPR.2018.00030http://dx.doi.org/10.1109/CVPR.2018.00030］
Häne C， Tulsiani S and Malik J. 2017. Hierarchical Surface Prediction for 3D Object Reconstruction //Proceedings of the International Conference on 3D Vision （3DV）. Qingdao， China， IEEE. 412-420 ［ DOI：10.1109/3DV.2017.00054http://dx.doi.org/10.1109/3DV.2017.00054］
He R Q， Jiang C H， Liu J S， Cao T and Gui W H. 2022. Blast Furnace Material Particle Size Detection Based on Concave-Convexity and Density-guided Point Cloud Segmentation ］//Proceedings of the China Automation Congress （CAC）. Xiamen， Fujian， China. 6.
何瑞清， 蒋朝辉， 刘金狮， 曹婷， 桂卫华. 2022. 基于凹凸性与密度引导点云分割的高炉炉料粒度检测 //中国自动化大会. 中国福建厦门. 6. ［ DOI：10.26914/c.cnkihy.2022.053812http://dx.doi.org/10.26914/c.cnkihy.2022.053812］
Ho L， Tran A T， Phung Q and Hoai M. 2021. Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Montreal， QC， Canada， IEEE. 12580-12590 ［ DOI：10.1109/ICCV48922.2021.01237http://dx.doi.org/10.1109/ICCV48922.2021.01237］
Hsu C， Chiu C and Kuan C. 2020. Fast Single-View 3D Object Reconstruction with Fine Details Through Dilated Downsample and Multi-Path Upsample Deep Neural Network //Proceedings of the IEEE International Conference on Acoustics， Speech and Signal Processing （ICASSP）. Barcelona， Spain， IEEE. 1653-1657 ［ DOI：10.1109/ICASSP40776.2020.9053607http://dx.doi.org/10.1109/ICASSP40776.2020.9053607］
Hu T， Wang L， Xu X， Liu S and Jia J. 2021. Self-Supervised 3D Mesh Reconstruction from Single Images］ //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， TN， USA， IEEE. 5998-6007 ［ DOI：10.1109/CVPR46437.2021.00594http://dx.doi.org/10.1109/CVPR46437.2021.00594］
Huang J， Jiang Z， Gui W， Yi Z， Pan D， Zhou K and Xu C. 2022a. Depth Estimation From a Single Image of Blast Furnace Burden Surface Based on Edge Defocus Tracking. IEEE Transactions on Circuits and Systems for Video Technology， 32（9）： 6044-6057 ［ DOI：10.1109/TCSVT.2022.3155626］
Huang Z， Jampani V， Thai A， Li Y， Stojanov S and Rehg J M. 2023. ShapeClipper： Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-Based Consistency //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， Bc， Canada. 12912-12922 ［ DOI：10.1109/CVPR52729.2023.01241http://dx.doi.org/10.1109/CVPR52729.2023.01241］
Huang Z， Stojanov S， Thai A， Jampani V and Rehg J M. 2022b. Planes vs. Chairs： Category-Guided 3D Shape Learning Without any 3D Cues //Proceedings of the European Conference on Computer Vision （ECCV）， Tel Aviv， Israel， Springer. 727-744 ［ DOI：10.48550/arXiv.2204.10235http://dx.doi.org/10.48550/arXiv.2204.10235］
Jin J， Xu H， Ji P and Leng B. 2022. IMC-NET： Learning Implicit Field with Corner Attention Network for 3D Shape Reconstruction //Proceedings of the IEEE International Conference on Image Processing （ICIP）. Bordeaux， France， IEEE. 1591-1595 ［ DOI：10.1109/ICIP46576.2022.9897709http://dx.doi.org/10.1109/ICIP46576.2022.9897709］
Kato H and Harada T. 2019. Learning View Priors for Single-View 3D Reconstruction //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Long Beach， CA， USA， IEEE. 9770-9779 ［ DOI：10.1109/CVPR.2019.01001http://dx.doi.org/10.1109/CVPR.2019.01001］
Kato H， Ushiku Y and Harada T. 2018. Neural 3D Mesh Renderer 3907-3916 //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， UT， USA， IEEE.［ DOI：10.1109/CVPR.2018.00411http://dx.doi.org/10.1109/CVPR.2018.00411］
Kim G and Chun S Y. 2023. DATID-3D： Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model 14203-14213 //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， BC， Canada， IEEE. ［ DOI：10.1109/CVPR52729.2023.01365http://dx.doi.org/10.1109/CVPR52729.2023.01365］
Kim Y M， Cho J and Ahn S C. 2016. 3D Modeling from Photos Given Topological Information. IEEE Transactions on Visualization and Computer Graphics， 22（9）： 2070-2081 ［ DOI：10.1109/TVCG.2015.2505307］
Kirillov A， Mintun E， Ravi N， Mao H， Rolland C， Gustafson L， Xiao T， Whitehead S， Berg A C， Lo W， Dollár P and Girshick R. Segment Anything. ［EB/OL］.［2023-04-05］. https://arxiv.org/pdf/2304.02643.pdfhttps://arxiv.org/pdf/2304.02643.pdf
Koch S， Matveev A， Jiang Z， Williams F， Artemov A， Burnaev E， Alexa M， Zorin D and Panozzo D. 2019. ABC： A Big CAD Model Dataset for Geometric Deep Learning //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Long Beach， CA， USA， IEEE. 9593-9603 ［ DOI：10.1109/CVPR.2019.00983http://dx.doi.org/10.1109/CVPR.2019.00983］
Kohli A P S， Sitzmann V and Wetzstein G. 2020. Semantic Implicit Neural Scene Representations With Semi-Supervised Training //Proceedings of the International Conference on 3D Vision （3DV）. Fukuoka， Japan， IEEE. 2020： 423-433 ［ DOI：10.1109/3DV50981.2020.00052http://dx.doi.org/10.1109/3DV50981.2020.00052］
Koneputugodage C H， Ben-Shabat Y and Gould S. 2023. Octree Guided Unoriented Surface Reconstruction //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， BC， Canada， IEEE. 16717-16726 ［ DOI：10.1109/CVPR52729.2023.01604http://dx.doi.org/10.1109/CVPR52729.2023.01604］
Kuo Y， Ko W， Chiu C and Chiu W. 2022. Improving Single-View Mesh Reconstruction for Unseen Categories via Primitive-Based Representation and Mesh Augmentation //Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. Kyoto， Japan， IEEE. 2001-2008 ［ DOI：10.1109/IROS47612.2022.9982024http://dx.doi.org/10.1109/IROS47612.2022.9982024］
Lai L， Chen J and Wu Q. 2024. Zero-Shot Single-View Point Cloud Reconstruction via Cross-Category Knowledge Transferring . IEEE Transactions on Multimedia， 26： 1448-1459 ［ DOI：10.1109/TMIM.2023.3282467］
Laradji I， Rodríguez P， Vazquez D and Nowrouzezahrai D. 2021. SSR： Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstruction //Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops （ICCVW）. Montreal， BC， Canada， IEEE. 1427-1436 ［ DOI：10.1109/ICCVW54120.2021.00164http://dx.doi.org/10.1109/ICCVW54120.2021.00164］
Lee J C， Rho D， Sun X， Ko J H and Park E. 2024. Compact 3D Gaussian Representation for Radiance Field //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， WA， USA， IEEE. 21719-21728 ［ DOI：10.48550/arXiv.2311.13681http://dx.doi.org/10.48550/arXiv.2311.13681］
Li J， Li D， Xiong C and Hoi S. 2022a. BLIP： Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation //Proceedings of the International Conference on Machine Learning （PMLR）. 12889-12901 ［ DOI：2201.12086http://dx.doi.org/2201.12086］
Li L and Wu S. 2021a. DmifNet： 3D Shape Reconstruction based on Dynamic Multi-Branch Information Fusion //Proceedings of the International Conference on Pattern Recognition （ICPR）. Milan， Italy， IEEE. 7219-7225 ［ DOI：10.1109/ICPR48806.2021.9411960http://dx.doi.org/10.1109/ICPR48806.2021.9411960］
Li L， Xu H and Wu S P. 2022b. Fuzzy probability points reasoning for 3D reconstruction via deep deterministic policy gradient. Acta Automatica Sinica， 48（4）： 1105-1118
李雷， 徐浩， 吴素萍. 2022b. 基于DDPG的三维重建模糊概率点推理. 自动化学报， 48（4）： 1105-1118 ［ DOI：10.16383/j.aas.c200543］
Li M and Zhang H. 2021b. D2IM-Net： Learning Detail Disentangled Implicit Fields from Single Images //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， TN， USA， IEEE. 10241-10250 ［ DOI：10.1109/CVPR46437.2021.01011http://dx.doi.org/10.1109/CVPR46437.2021.01011］
Li R， Han B， Li H， Ma L， Zhang X， Zhao Z and Liao H. 2024. A Comparative Evaluation of Optical See-Through Augmented Reality in Surgical Guidance. IEEE Transactions on Visualization and Computer Graphics， 30（7）： 4362-4374 ［ DOI：10.1109/TVCG.2023.3260001］
Li X and Kuang P. 2021c. 3D-VRVT： 3D Voxel Reconstruction from A Single Image with Vision Transformer //Proceedings of the International Conference on Culture-oriented Science \& Technology （ICCST）. Beijing， China， IEEE. 343-348 ［ DOI：10.1109/ICCST53801.2021.00078http://dx.doi.org/10.1109/ICCST53801.2021.00078］
Li Z and Snavely N. 2018. MegaDepth： Learning Single-View Depth Prediction from Internet Photos //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， UT， USA， IEEE. 2041-2050 ［ DOI：10.1109/CVPR.2018.00218http://dx.doi.org/10.1109/CVPR.2018.00218］
Liang C Y ， Tang H M ， Xi J R and Liu X. 2023. Improved single-view surface reconstruction based on sparse feature. Application Research of Computers， 40（3）： 925-931，937.
梁春阳， 唐红梅， 席建锐， 刘鑫. 2023. 基于稀疏特征改进的单视图表面重建. 计算机应用研究， 40（3）： 925-931，937 ［ DOI：10.19734/j.issn.1001-3695.2022.06.0320］
Lim J J， Pirsiavash H and Torralba A. 2013. Parsing IKEA Objects： Fine Pose Estimation //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）.Australia， IEEE. 2992-2999 ［ DOI：10.1109/ICCV.2013.372http://dx.doi.org/10.1109/ICCV.2013.372］
Liu J， Mills S and McCane B. 2020. RocNet： Recursive Octree Network for Efficient 3D Deep Representation //Proceedings of the International Conference on 3D Vision （3DV）. Fukuoka， Japan， IEEE. 414-422 ［ DOI：10.1109/3DV50981.2020.00051http://dx.doi.org/10.1109/3DV50981.2020.00051］
Liu M， Shi R， Chen L， Zhang Z， Xu C， Wei X， Chen H， Zeng C， Gu J and Su H. 2023a. One-2-3-45++： Fast single image to 3d objects with consistent multi-view generation and 3d diffusion //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 10072-10083 ［DOI：10.48550/arXiv.2311.07885http://dx.doi.org/10.48550/arXiv.2311.07885］
Liu M， Xu C， Jin H， Chen L， T M V， Xu Z and Su H. 2024a. One-2-3-45： any single image to 3D mesh in 45 seconds without per-shape optimization //Proceedings of the 37th International Conference on Neural Information Processing Systems （NIPS）. New Orleans， LA， USA， Curran Associates Inc.. 21 ［DOI：10.48550/arXiv.2306.16928］
Liu M， Xu C， Jin H， Chen L， T M V， Xu Z and Su H. 2024b. One-2-3-45： any single image to 3D mesh in 45 seconds without per-shape optimization //Proceedings of the 37th International Conference on Neural Information Processing Systems （NIPS）. New Orleans， LA， USA， Curran Associates Inc.. 21 ［DOI：10.48550/arXiv.2306.16928］
Liu R， Wu R， Van Hoorick B， Tokmakov P， Zakharov S and Vondrick C. 2023b. Zero-1-to-3： Zero-shot One Image to 3D Object //Proceedings of the IEEE/CVF International Conference on Computer Vision （CVPR）. Paris， France， IEEE. 9264-9275 ［ DOI：10.1109/ICCV51070.2023.00853http://dx.doi.org/10.1109/ICCV51070.2023.00853］
Liu S， Chen W， Li T and Li H. 2019. Soft Rasterizer： A Differentiable Renderer for Image-Based 3D Reasoning //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）， IEEE. 7707-7716 ［ DOI：10.1109/ICCV.2019.00780http://dx.doi.org/10.1109/ICCV.2019.00780］
Liu X N， Chen C Y， Hu X J and Yu H Y. 2024. Virtual viewpoint image synthesis using neural radiance fields with depth information supervision. Journal of Image and Graphics， 29（07）： 2035-2045
刘晓楠，陈纯毅，胡小娟，于海洋. 2024. 带深度信息监督的神经辐射场虚拟视点画面合成. 中国图象图形学报， 29（07）： 2035-2045［DOI： 10. 11834/jig. 221188http://dx.doi.org/10.11834/jig.221188］
Liu Z， Tang S and Wang Y. 2015. Single view reconstruction based on marker and geometric constraints //Proceedings of the International Congress on Image and Signal Processing （CISP）. Shenyang， China， IEEE. 1058-1062 ［ DOI：10.1109/CISP.2015.7408036http://dx.doi.org/10.1109/CISP.2015.7408036］
Loper M M and Black M J. 2014. OpenDR： An Approximate Differentiable Renderer //Proceedings of the the European Conference on Computer Vision （ECCV）. Zurich， Switzerland， Springer. 154-169 ［ DOI：10.1007/978-3-319-10584-0_11http://dx.doi.org/10.1007/978-3-319-10584-0_11］
Lu J W， Guo C， Dai X Y， Miao Q H， Wang X X， Yang J and Wang F Y. The ChatGPT after： Opportunities and challenges of very large scale pre-trained models［J］. Acta Automatica Sinica， 2023， 49（4）： 705-717.
卢经纬， 郭超， 戴星原， 缪青海， 王兴霞， 杨静， 王飞跃. 2023. 问答ChatGPT之后：超大预训练模型的机遇和挑战. 自动化学报， 49（4）： 705-717 ［ DOI：10.16383/j.aas.c230107］
Mei J， Yu J， Romain S， Rose C， Magrane K， LeeSon G and Hwang J. 2022. Unsupervised Severely Deformed Mesh Reconstruction （DMR） From A Single-View Image for Longline Fishing.//Proceedings of the IEEE International Conference on Multimedia and Expo Workshops （ICMEW）. Taipei City， Taiwan， IEEE. 1-6 ［DOI：10.1109/ICMEW56448.2022.9859312http://dx.doi.org/10.1109/ICMEW56448.2022.9859312］
Melas-Kyriazi L， Rupprecht C and Vedaldi A. 2023. PC2： Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， BC， Canada， IEEE. 12923-12932 ［ DOI：10.1109/CVPR52729.2023.01242http://dx.doi.org/10.1109/CVPR52729.2023.01242］
Mescheder L， Oechsle M， Niemeyer M， Nowozin S and Geiger A. 2019. Occupancy Networks： Learning 3D Reconstruction in Function Space //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Long Beach， CA， USA， IEEE. 4455-4465 ［ DOI：10.1109/CVPR.2019.00459http://dx.doi.org/10.1109/CVPR.2019.00459］
Michalkiewicz M， Parisot S， Tsogkas S， Baktashmotlagh M， Eriksson A and Belilovsky E. 2020. Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors //Proceedings of the European Conference on Computer Vision （ECCV）. Glasgow， UK， Springer. 614-630 ［ DOI：10.1007/978-3-030-58595-2_37http://dx.doi.org/10.1007/978-3-030-58595-2_37］
Mildenhall B， Srinivasan P P， Tancik M， Barron J T， Ramamoorthi R and Ng R. 2020. NeRF： Representing Scenes as Neural Radiance Fields for View Synthesis //Proceedings of the European Conference on Computer Vision （ECCV）. Glasgow， UK， Springer. 405-421 ［ DOI：10.1007/978-3-030-58452-8_24http://dx.doi.org/10.1007/978-3-030-58452-8_24］
Mo K， Zhu S， Chang A X， Yi L， Tripathi S， Guibas L J and Su H. 2019. PartNet： A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Long Beach， CA， USA， IEEE. 909-918 ［ DOI：10.1109/CVPR.2019.00100http://dx.doi.org/10.1109/CVPR.2019.00100］
Monnier T， Fisher M， Efros A A and Aubry M. 2022. Share with Thy Neighbors： Single-View Reconstruction by Cross-Instance Consistency //Proceedings of the European Conference on Computer Vision （ECCV）， Tel Aviv， Israel， Springer. 285-303 ［ DOI：10.1007/978-3-031-19769-7_17http://dx.doi.org/10.1007/978-3-031-19769-7_17］
Nam H， Jung D S， Oh Y and Lee K M. 2023. Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， BC， Canada， IEEE. 14783-14793 ［ DOI：10.1109/ICCV51070.2023.01362http://dx.doi.org/10.1109/ICCV51070.2023.01362］
Nie W， Jiao C， Chang R， Qu L and Liu A. 2023a. CPG3D： Cross-Modal Priors Guided 3D Object Reconstruction. IEEE Transactions on Multimedia， 25（｛｝）： 9383-9396 ［ DOI：10.1109/TMM.2023.3251697］
Nie Y， Dai A， Han X and NieBner M. 2023b. Learning 3D Scene Priors with 2D Supervision //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， BC， Canada， IEEE. 792-802 ［ DOI：10.1109/CVPR52729.2023.00083http://dx.doi.org/10.1109/CVPR52729.2023.00083］
Niemeyer M， Mescheder L， Oechsle M and Geiger A. 2020. Differentiable Volumetric Rendering： Learning Implicit 3D Representations Without 3D Supervision //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 3501-3512 ［ DOI：10.1109/CVPR42600.2020.00356http://dx.doi.org/10.1109/CVPR42600.2020.00356］
Park J J， Florence P， Straub J， Newcombe R and Lovegrove S. 2019. DeepSDF： Learning Continuous Signed Distance Functions for Shape Representation //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Long Beach， CA， USA， IEEE. 165-174 ［ DOI：10.1109/CVPR.2019.00025http://dx.doi.org/10.1109/CVPR.2019.00025］
Park K， Kim S and Sohn K. 2020. High-Precision Depth Estimation Using Uncalibrated LiDAR and Stereo Fusion. IEEE Transactions on Intelligent Transportation Systems， 21（1）： 321-335 ［ DOI：10.1109/TITS.2019.2891788］
Park K， Sinha U， Barron J T， Bouaziz S， Goldman D B， Seitz S M and Martin-Brualla R. 2021. Nerfies： Deformable Neural Radiance Fields //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Montreal， QC， Canada， IEEE. 5845-5854 ［ DOI：10.1109/ICCV48922.2021.00581http://dx.doi.org/10.1109/ICCV48922.2021.00581］
Peng S， Niemeyer M， Mescheder L， Pollefeys M and Geiger A. 2020. Convolutional Occupancy Networks //Proceedings of the European Conference on Computer Vision （ECCV）. Glasgow， UK， Springer. 523-540 ［ DOI：10.1007/978-3-030-58580-8_31http://dx.doi.org/10.1007/978-3-030-58580-8_31］
Piao J， Qian C and Li H. 2019. Semi-Supervised Monocular 3D Face Reconstruction With End-to-End Shape-Preserved Domain Transfer //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）， IEEE. 9397-9406 ［ DOI：10.1109/ICCV.2019.00949http://dx.doi.org/10.1109/ICCV.2019.00949］
Pinheiro P O， Rostamzadeh N and Ahn S. 2019. Domain-Adaptive Single-View 3D Reconstruction //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）， IEEE. 7637-7646 ［ DOI：10.1109/ICCV.2019.00773http://dx.doi.org/10.1109/ICCV.2019.00773］
Pumarola A， Agudo A， Porzi L， Sanfeliu A， Lepetit V and Moreno-Noguer F. 2018. Geometry-Aware Network for Non-rigid Shape Prediction from a Single View //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， UT， USA， IEEE. 4681-4690 ［ DOI：10.1109/CVPR.2018.00492http://dx.doi.org/10.1109/CVPR.2018.00492］
Rebain D， Matthews M， Yi K M， Lagun D and Tagliasacchi A. 2022. LOLNeRF： Learn from One Look //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. New Orleans， LA， USA， IEEE. 1548-1557 ［ DOI：10.1109/CVPR52688.2022.00161http://dx.doi.org/10.1109/CVPR52688.2022.00161］
Riegler G， Ulusoy A O and Geiger A. 2017. OctNet： Learning Deep 3D Representations at High Resolutions //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Honolulu， HI， USA， IEEE. 6620-6629 ［ DOI：10.1109/CVPR.2017.701http://dx.doi.org/10.1109/CVPR.2017.701］
Roessle B， Barron J T， Mildenhall B， Srinivasan P P and Nießner M. 2022. Dense Depth Priors for Neural Radiance Fields from Sparse Input Views //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. New Orleans， LA， USA， IEEE. 12882-12891 ［ DOI：10.1109/CVPR52688.2022.01255http://dx.doi.org/10.1109/CVPR52688.2022.01255］
Taha S and Mohsen S. 2023. Deep learning-based 3D reconstruction： a survey. Artificial Intelligence Review： An International Science and Engineering Journal， 56（9）： 9175-9219 ［ DOI：10.1007/s10462-023-10399-2］
Seo J， Jang W， Kwak M， Kim H， Ko J， Kim J， Kim J， Lee J and Kim S. Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation. ［EB/OL］.［2024-02-06］. https://arxiv.org/pdf/2303.07937.pdfhttps://arxiv.org/pdf/2303.07937.pdf
Shen Q， Yang X and Wang X. Anything-3D： Towards Single-view Anything Reconstruction in the Wild. ［EB/OL］.［2023-04-19］. https://arxiv.org/pdf/2304.10261.pdfhttps://arxiv.org/pdf/2304.10261.pdf
Shen W C， Ma T S， Wu Y W and Jia Y D. 2021. Component-Aware High-Resolution 3D Object Reconstruction. Journal of Computer-Aided Design & Computer Graphics， 33（12）： 1887-1898.
沈伟超， 马天朔， 武玉伟， 贾云得. 2021. 组件感知的高分辨率三维物体重建方法. 计算机辅助设计与图形学学报， 33（12）： 1887-1898 ［ DOI：10.3724/SP.J.1089.2021.18805］
Silberman N， Hoiem D， Kohli P and Fergus R. 2012. Indoor Segmentation and Support Inference from RGBD Images //Proceedings of the the European Conference on Computer Vision （ECCV）. Florence， Italy， Springer. 746-760 ［ DOI：10.1007/978-3-642-33715-4_54http://dx.doi.org/10.1007/978-3-642-33715-4_54］
Sitzmann V， Zollhofer M and Wetzstein G. 2020. Scene Representation Networks： Continuous 3D-Structure-Aware Neural Scene Representations //Proceedings of the Advances in Neural Information Processing Systems （NIPS）. Red Hook， NY， USA， Inc. 1121-1132 ［ DOI：10.48550/arXiv.1906.01618http://dx.doi.org/10.48550/arXiv.1906.01618］
Song S， Lichtenberg S P and Xiao J. 2015. SUN RGB-D： A RGB-D scene understanding benchmark suite //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Boston， MA， USA， IEEE. 567-576 ［ DOI：10.1109/CVPR.2015.7298655http://dx.doi.org/10.1109/CVPR.2015.7298655］
Sun X， Wu J， Zhang X， Zhang Z， Zhang C， Xue T， Tenenbaum J B and Freeman W T. 2018a. Pix3D： Dataset and Methods for Single-Image 3D Shape Modeling //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， UT， USA， IEEE. 2974-2983 ［ DOI：10.1109/CVPR.2018.00314http://dx.doi.org/10.1109/CVPR.2018.00314］
Sun Y， Liu Z， Wang Y and Sarma S E. Im2Avatar： Colorful 3D Reconstruction from a Single Image. ［EB/OL］.［ 2018b-04-17］. https://arxiv.org/pdf/1804.06375.pdfhttps://arxiv.org/pdf/1804.06375.pdf
Szymanowicz S， Rupprecht C and Vedaldi A. 2024. Splatter Image： Ultra-Fast Single-View 3D Reconstruction //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 10208-10217 ［ DOI：10.48550/arXiv.2312.13150http://dx.doi.org/10.48550/arXiv.2312.13150］
Tatarchenko M， Dosovitskiy A and Brox T. 2017. Octree Generating Networks： Efficient Convolutional Architectures for High-resolution 3D Outputs //Proceedings of the IEEE International Conference on Computer Vision （ICCV）. Venice， Italy， IEEE. 2107-2115 ［ DOI：10.1109/ICCV.2017.230http://dx.doi.org/10.1109/ICCV.2017.230］
Tian Y， Zhang H， Liu Y and Wang L. 2023. Recovering 3D Human Mesh From Monocular Images： A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence， 45（12）： 15406-15425 ［ DOI：10.1109/TPAMI.2023.3298850］
Tulsiani S， Efros A A and Malik J. 2018. Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， UT， USA， IEEE. 2897-2905 ［ DOI：10.1109/CVPR.2018.00306http://dx.doi.org/10.1109/CVPR.2018.00306］
Tulsiani S， Zhou T， Efros A A and Malik J. 2017. Multi-view Supervision for Single-View Reconstruction via Differentiable Ray Consistency. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 44（12）： 8754-8765. ［ DOI：10.1109/CVPR.2017.30］
Victoria C， Torres F， Garduño E， Cosío F A and Gastelum-Strozzi A. 2023. Real-Time 3D Ultrasound Reconstruction Using Octrees. IEEE Access， 11（｛｝）： 78970-78983 ［ DOI：10.1109/ACCESS.2023.3298887］
Wang J and Fang Z. 2020a. GSIR： Generalizable 3D Shape Interpretation and Reconstruction //Proceedings of the European Conference on Computer Vision （ECCV）. Glasgow， UK， Springer. 498-514 ［ DOI： 10.1007/978-3-030-58601-0_30http://dx.doi.org/10.1007/978-3-030-58601-0_30］
Wan J H， Liu X P， Chen L L， Ao S， Zhang P and Guo Y L. 2024. Geometric attribute-guided 3D semantic instance reconstruction. Journal of Image and Graphics， 29（01）： 0218-0230
万骏辉，刘心溥，陈莉丽，敖晟，张鹏，郭裕兰. 2024. 几何属性引导的三维语义实例重建. 中国图象图形学报，29（01）： 0218-0230［DOI：10. 11834/jig. 230106http://dx.doi.org/10.11834/jig.230106］
Wang K， Kemao Q， Di J and Zhao J. 2022. Deep learning spatial phase unwrapping： a comparative review. Advanced Photonics Nexus， 2022， 1（1）： 014001-014001. ［DOI：10.1117/1.APN.1.1.014001http://dx.doi.org/10.1117/1.APN.1.1.014001］
Wang N， Zhang Y， Li Z， Fu Y， Liu W and Jiang Y. 2018a. Pixel2Mesh： Generating 3D Mesh Models from Single RGB Images //Proceedings of the European Conference on Computer Vision （ECCV）. Munich， Germany， Springer. 55-71 ［ DOI：10.48550/arXiv.1804.01654http://dx.doi.org/10.48550/arXiv.1804.01654］
Wang N， Hu X Y， Zhu F and Tang J. 2020b. Single-view 3D Reconstruction Algorithm Based on View-aware. Journal of Electronics & Information Technology， 42（12）： 3053-3060.
王年， 胡旭阳， 朱凡， 唐俊. 2020b. 基于视图感知的单视图三维重建算法. 电子与信息学报， 2020， 42（12）： 3053-3060 ［DOI：10.11999/JEIT190986http://dx.doi.org/10.11999/JEIT190986］
Wang P， Liu Y， Guo Y， Sun C and Tong X. 2017. O-CNN： Octree-based Convolutional Neural Networks for 3D Shape Analysis. ACM Transactions On Graphics （TOG）， 2017， 36（4）： 1-11. ［ DOI：10.1145/3072959.3073608］
Wang P， Liu Y， Guo Y， Sun C and Tong X. 2018b. Adaptive O-CNN： A Patch-based Deep Representation of 3D Shapes. ACM Transactions on Graphics （TOG）， 2018， 37（6）： 1-11. ［ DOI：10.1145/3272127.3275050］
Wang W， Xu Q， Ceylan D， Mech R and Neumann U. 2020c. DISN： Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction //Proceedings of Advances in Neural Information Processing Systems （NIPS）. Red Hook， NY， USA， Inc. 492-502 ［ DOI：10.48550/arXiv.1905.10711http://dx.doi.org/10.48550/arXiv.1905.10711］
Wang Y， He X， Peng S， Lin H， Bao H and Zhou X. 2023a. AutoRecon： Automated 3D Object Discovery and Reconstruction //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， BC， Canada， IEEE. 21382-21391 ［ DOI：10.1109/CVPR52729.2023.02048http://dx.doi.org/10.1109/CVPR52729.2023.02048］
Wang Y， Lira W， Wang W， Mahdavi-Amiri A and Zhang H. 2023b. Slice3D： Multi-Slice， Occlusion-Revealing， Single View 3D Reconstruction //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle， WA， USA， IEEE. ［ DOI：10.48550/arXiv.2312.02221http://dx.doi.org/10.48550/arXiv.2312.02221］
Wimbauer F， Yang N， Rupprecht C and Cremers D. 2023. Behind the Scenes： Density Fields for Single View Reconstruction //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， BC， Canada， IEEE. 9076-9086 ［ DOI：10.1109/CVPR52729.2023.00876http://dx.doi.org/10.1109/CVPR52729.2023.00876］
Woo S， Park J， Lee J and Kweon I S. 2018. CBAM： Convolutional Block Attention Module //Proceedings of the European Conference on Computer Vision （ECCV）. Munich， Germany， Springer. 2018： 3-19. ［ DOI：10.48550/arXiv.1807.06521http://dx.doi.org/10.48550/arXiv.1807.06521］
Wu F and He S X. 2023.Single-view 3D reconstruction based on attentional mechanisms. Laser Journal， 2023a， 44（1）： 109-114. （吴繁， 贺赛先. 2023.基于注意力机制的单视图三维重建. 激光杂志， 2023a， 44（1）： 109-114.） ［ DOI：10.14016/j.cnki.jgzz.2023.01.109］
Wu J， Wang Y， Xue T， Sun X， Freeman W T and Tenenbaum J B. 2017. MarrNet： 3D Shape Reconstruction via 2.5D Sketches//Proceedings of Advances in Neural Information Processing Systems （NIPS）. Long Beach， California， USA， Inc. 2017： 540-550. ［ DOI：10.48550/arXiv.1711.03129http://dx.doi.org/10.48550/arXiv.1711.03129］
Wu J， Zhang C， Zhang X， Zhang Z， Freeman W T and Tenenbaum J B. 2018. Learning Shape Priors for Single-View 3D Completion and Reconstruction //Proceedings of the European Conference on Computer Vision （ECCV）. Munich， Germany， Springer. 673-691. ［ DOI：10.14016/j.cnki.jgzz.2023.01.109http://dx.doi.org/10.14016/j.cnki.jgzz.2023.01.109］
Wu S， Li R， Jakab T， Rupprecht C and Vedaldi A. 2023b. MagicPony： Learning Articulated 3D Animals in the Wild //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8792-8802 ［ DOI：10.1109/CVPR52729.2023.00849http://dx.doi.org/10.1109/CVPR52729.2023.00849］
Wu S， Rupprecht C and Vedaldi A. 2023c. Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild （Invited Paper）. IEEE Transactions on Pattern Analysis and Machine Intelligence， 45（4）： 5268-5281 ［ DOI：10.1109/TPAMI.2021.3076536］
Wu Z， Song S， Khosla A， Yu F， Zhang L， Tang X and Xiao J. 2015a. 3D ShapeNets： A deep representation for volumetric shapes //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Boston， MA， USA， IEEE. 1912-1920 ［ DOI：10.1109/CVPR.2015.7298801http://dx.doi.org/10.1109/CVPR.2015.7298801］
Wu Z， Song S， Khosla A， Yu F， Zhang L， Tang X and Xiao J. 2015b. 3D ShapeNets： A deep representation for volumetric shapes //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Boston， MA， USA， IEEE. 1912-1920 ［ DOI：10.1109/CVPR.2015.7298801http://dx.doi.org/10.1109/CVPR.2015.7298801］
Xiang Y， Kim W， Chen W， Ji J， Choy C， Su H， Mottaghi R， Guibas L and Savarese S. 2016. ObjectNet3D： A Large Scale Database for 3D Object Recognition //Proceedings of the the European Conference on Computer Vision （ECCV）. Amsterdam， The Netherlands， Springer. 160-176 ［ DOI： 10.1007/978-3-319-46484-8_10http://dx.doi.org/10.1007/978-3-319-46484-8_10］
Xiang Y， Mottaghi R and Savarese S. 2014. Beyond PASCAL： A benchmark for 3D object detection in the wild //Proceedings of the IEEE Winter Conference on Applications of Computer Vision （WACV）. Steamboat Springs， CO， IEEE. 75-82 ［ DOI：10.1109/WACV.2014.6836101http://dx.doi.org/10.1109/WACV.2014.6836101］
Xie H， Yao H， Sun X， Zhou S and Zhang S. 2019. Pix2Vox： Context-Aware 3D Reconstruction From Single and Multi-View Images //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）， IEEE. 2690-2698 ［ DOI：10.1109/ICCV.2019.00278http://dx.doi.org/10.1109/ICCV.2019.00278］
Xing Z， Li H， Wu Z and Jiang Y. 2022. Semi-supervised Single-View 3D Reconstruction via Prototype Shape Priors //Proceedings of the European Conference on Computer Vision （ECCV）， Tel Aviv， Israel， Springer. 535-551 ［ DOI：10.1007/978-3-031-19769-7_31http://dx.doi.org/10.1007/978-3-031-19769-7_31］
Xu H， Zhou Z， Qiao Y， Kang W and Wu Q. 2021a. Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation //Proceedings of the Conference on Artificial Intelligence （AAAI） 3030-3038 ［ DOI：10.1609/aaai.v35i4.16411http://dx.doi.org/10.1609/aaai.v35i4.16411］
Xu H， Zhou Z， Wang Y， Kang W， Sun B， Li H and Qiao Y. 2021b. Digging into Uncertainty in Self-supervised Multi-view Stereo //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Montreal， QC， Canada， IEEE. 6058-6067 ［ DOI：10.1109/ICCV48922.2021.00602http://dx.doi.org/10.1109/ICCV48922.2021.00602］
Xu J， Cheng W， Gao Y， Wang X， Gao S and Shan Y. InstantMesh： Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models ［EB/OL］. ［2024-04-14］. https://arxiv.org/pdf/2404.07191.pdfhttps://arxiv.org/pdf/2404.07191.pdf
Yang C， Xie H， Tian H and Yu Y. 2021a. Dynamic Domain Adaptation for Single-view 3D Reconstruction //Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems （IROS）. Prague， Czech Republic， IEEE. 3563-3570 ［ DOI：10.1109/IROS51168.2021.9636343http://dx.doi.org/10.1109/IROS51168.2021.9636343］
Yang G， Cui Y， Belongie S and Hariharan B. 2018. Learning Single-View 3D Reconstruction with Limited Pose Supervision //Proceedings of the European Conference on Computer Vision （ECCV）. Munich， Germany， Springer. 90-105 ［ DOI：10.1007/978-3-030-01267-0_6http://dx.doi.org/10.1007/978-3-030-01267-0_6］
Yang H， Chen R， An S P， Wei H and Zhang H. 2023. The growth of image-related three dimensional reconstruction techniques in deep learning-driven era：a critical summary. Journal of image and Graphics， 2023， 28（8）： 2396-2409
杨航， 陈瑞， 安仕鹏， 魏豪， 张衡. 2023. 深度学习背景下的图像三维重建技术进展综述. 中国图象图形学报， 2023， 28（8）： 2396-2409 ［ DOI： 10.11834/jig.220376］
Yang S， Xu M， Xie H， Perry S and Xia J. 2021b. Single-View 3D Object Reconstruction from Shape Priors in Memory //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， TN， USA， IEEE. 3151-3160 ［ DOI：10.1109/CVPR46437.2021.00317http://dx.doi.org/10.1109/CVPR46437.2021.00317］
Yang X， Lin G and Zhou L. 2023. Single-View 3D Mesh Reconstruction for Seen and Unseen Categories. IEEE Transactions on Image Processing， 32（｛｝）： 3746-3758 ［ DOI：10.1109/TIP.2023.3279661］
Yao C， Hung W， Jampani V and Yang M. 2021. Discovering 3D Parts from Image Collections //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Montreal， QC， Canada， IEEE. 12961-12970 ［ DOI：10.1109/ICCV48922.2021.01274http://dx.doi.org/10.1109/ICCV48922.2021.01274］
Yao Y， Schertler N， Rosales E， Rhodin H， Sigal L and Sheffer A. 2020. Front2Back： Single View 3D Shape Reconstruction via Front to Back Prediction //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 528-537 ［ DOI：10.1109/CVPR42600.2020.00061http://dx.doi.org/10.1109/CVPR42600.2020.00061］
Yue M， Fu G， Wu M and Wang H. 2020. Semi-Supervised Monocular Depth Estimation Based on Semantic Supervision. Journal of Intelligent and Robotic Systems， 2020， 100（2）： 455-463. ［ DOI：10.1007/s10846-020-01205-0］
Zamir A R， Sax A， Cheerla N， Suri R， Cao Z， Malik J and Guibas L J. 2020. Robust Learning Through Cross-Task Consistency //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 11194-11203 ［ DOI：10.1109/CVPR42600.2020.01121http://dx.doi.org/10.1109/CVPR42600.2020.01121］
Zhang H， Zhang Q， Li Y X， et al. Research on 3D model reconstruction based on deep learning［J］. Journal of Chongqing University of Posts and Telecommunications（Natural Science Edition）， 2021a， 33（2）： 289-295. （张豪， 张强， 李勇祥， 邵思羽. 2021. 基于深度学习的三维模型重构研究. 重庆邮电大学学报（自然科学版）， 2021a， 33（2）： 289-295 ［ DOI：10.3979/j.issn.1673-825X.201911040383http://dx.doi.org/10.3979/j.issn.1673-825X.201911040383］
Zhang T， Bian N， Liu Q and Du Y. 2023a. 3D super-resolution reconstruction of porous media based on GANs and CBAMs. Stochastic Environmental Research and Risk Assessment， 2023： 1-30. ［ DOI：10.1016/j.petrol.2021.109815］
Zhang X， Zhang Z， Zhang C， Tenenbaum J B， Freeman W T and Wu J. 2018. Learning to Reconstruct Shapes from Unseen Classes //Proceedings of Advances in Neural Information Processing Systems （NIPS）. Red Hook， NY， USA， Inc. 2263-2274. ［ DOI：10.48550/arXiv.1812.11166http://dx.doi.org/10.48550/arXiv.1812.11166］
Zhang Y， Tosi F， Mattoccia S and Poggi M. 2023b. GO-SLAM： Global Optimization for Consistent 3D Instant Reconstruction //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Paris， France， IEEE. 3704-3714 ［ DOI：10.1109/ICCV51070.2023.00345http://dx.doi.org/10.1109/ICCV51070.2023.00345］
Zhao F， Wang W， Liao S and Shao L. 2021. Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction //Proceedings of the IEEE International Conference on Computer Vision （ICCV）. Montreal， QC， Canada， IEEE. 12654-12663 ［ DOI：10.1109/ICCV48922.2021.01244http://dx.doi.org/10.1109/ICCV48922.2021.01244］
Zheng S， Bao Z， Hebert M and Wang Y. 2023. Multi-task View Synthesis with Neural Radiance Fields //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Paris， France， IEEE. 21481-21492 ［ DOI：10.1109/ICCV51070.2023.01969http://dx.doi.org/10.1109/ICCV51070.2023.01969］
Zhou C， Zhang Y， Chen J and Huang D. 2023a. OcTr： Octree-Based Transformer for 3D Object Detection //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， BC， Canada， IEEE. 5166-5175 ［ DOI：10.1109/CVPR52729.2023.00500http://dx.doi.org/10.1109/CVPR52729.2023.00500］
Zhou H， Liu J， Liu Z， Liu Y and Wang X. 2020a. Rotate-and-Render： Unsupervised Photorealistic Face Rotation From Single-View Images //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 5910-5919 ［DOI：10.1109/CVPR42600.2020.00595http://dx.doi.org/10.1109/CVPR42600.2020.00595］
Zhou X Q， Wang X， Zheng J and Bai X. Adaptive Spatial Sparsification for Efficient Multi-View Stereo Matching. Acta Electronica Sinica， 2023b， 51（11）： 3079-3091. （周晓清， 王翔， 郑锦， 百晓. 2023b. 基于自适应空间稀疏化的高效多视图立体匹配. 电子学报， 2023， 51（11）： 3079-3091 ［ DOI：10.12263/DZXB.20230353http://dx.doi.org/10.12263/DZXB.20230353］
Zhou Y， Liu S and Ma Y. 2020. Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction. ［EB/OL］. ［2020-06-17］. https://arxiv.org/pdf/2006.10042.pdfhttps://arxiv.org/pdf/2006.10042.pdf
Zhou Y， Shen Y， Yan Y， Feng C and Yang Y. 2021. A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks //Proceedings of the International Conference on 3D Vision （3DV）. London， United Kingdom， IEEE. 1331-1340 ［ DOI：10.1109/3DV53792.2021.00140http://dx.doi.org/10.1109/3DV53792.2021.00140］
Zhu Y Z， Zhang Y P and Feng Q S. 2021. Colorful 3D Reconstruction from Single Image Based on Deep Learning. Laser & Optoelectronics Progress， 2021， 58（14）： 199-207.
朱育正， 张亚萍， 冯乔生. 2021. 基于深度学习的单视图彩色三维重建. 激光与光电子学进展， 2021， 58（14）： 199-207 ［ DOI：10.3788/LOP202158.1410010.］
Zhu Z， Yang L， Li N， Jiang C and Liang Y. 2023. UMIFormer： Mining the Correlations between Similar Tokens for Multi-View 3D Reconstruction //Proceedings of the IEEE/CVF International Conference on Computer Vision （ICCV）. Paris， France， IEEE. 18180-18189 ［ DOI：10.1109/ICCV51070.2023.01671http://dx.doi.org/10.1109/ICCV51070.2023.01671］
Zou Z， Yu Z， Guo Y， Li Y， Liang D， Cao Y and Zhang S. 2024. Triplane Meets Gaussian Splatting： Fast and Generalizable Single-View 3D Reconstruction with Transformers //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， WA， USA， IEEE. 10324-10335 ［ DOI：10.48550/arXiv.2312.09147http://dx.doi.org/10.48550/arXiv.2312.09147］
Zubi N and Liò P. 2021. An Effective Loss Function for Generating 3D Models from Single 2D Image Without Rendering //Proceedings of the Artificial Intelligence Applications and Innovations （AIAI）. Hersonissos， Crete， Greece， Springer. 309-322 ［ DOI：10.48550/arXiv.2103.03390http://dx.doi.org/10.48550/arXiv.2103.03390］
相关作者
相关机构
京公网安备11010802024621