浏览全部资源
扫码关注微信
纸质出版日期： 2025-02-16 ，
移动端阅览
徐正国， 普碧才， 秦建明， 项炎平， 彭振江， 宋纯锋. 2025. 面向高清人体图像生成的数据基准与模型框架. 中国图象图形学报， 30(02):0375-0390
Xu Zhengguo， Pu Bicai， Qin Jianming， Xiang Yanping， Peng Zhenjiang， Song Chunfeng. 2025. Data benchmark and model framework for high-definition human image generation. Journal of Image and Graphics， 30(02):0375-0390
目的
2
姿态引导下的人物图像生成具有广泛的应用潜力，受到了广泛关注。低分辨率场景的姿态引导人物图像生成任务取得了很大成功。然而在高分辨率场景下，现有的人体姿态迁移数据集存在分辨率低或多样性差等问题，同时也缺乏相关高分辨率图像生成方法。针对这一问题，构建了具有多模态辅助数据的大规模高清人物图像数据集PersonHD。
方法
2
PersonHD数据集收集了包含100个不同人物的299 817幅图像。在提出的PersonHD基础上，基于现有数据集的公共设置，本文进一步构建了两个不同分辨率下的评测基准，并设计了一个实用的高分辨率人物图像生成框架，为评估最先进的姿态引导人物图像生成方法提供了一个新的平台。
结果
2
与现有数据集相比，PersonHD在更高的图像分辨率、更多样化的人物姿态和更大规模的样本方面具有显著的优势。基于PersonHD数据集，实验在两个不同分辨率的评测基准上系统地评估了当前具有代表性的姿态引导人物图像生成方法，并对本文提出框架各模块的有效性进行了系统验证。实验结果表明，该框架具有良好的效果。
结论
2
本文提出的高清人物图像生成基准数据集具有高分辨率数据规模大、多样性强等特点，有助于更为全面地评估姿态引导下的人物图像生成算法。本文的数据集和代码可在
https://github.com/BraveGroup/PersonHD
https://github.com/BraveGroup/PersonHD
上获得。
Objective
2
Pose-guided person image generation has attracted considerable attention because of its wide application potential. In the early stages of development， researchers relied mainly on manually designing features and models， matching key points between different characters， and then achieving pose transfer via interpolation or transformation. With the rapid development of deep learning technology， the emergence of generative adversarial networks （GANs） has led to considerable progress in posture transfer. GANs can learn and generate realistic images， and variants of related generative adversarial networks have been widely used in pose transfer tasks. Moreover， deep learning has made progress in key point detection technology. Advanced key point detection models， such as OpenPose， can more accurately capture human pose information， providing tremendous assistance for the development of algorithms in related fields and the construction of datasets. Recent works have achieved great success in pose-guided person image generation tasks with low-definition scenes. However， in high-resolution scenes， existing human pose transfer datasets suffer from low resolution or poor diversity， and relevant high-resolution image generation methods are lacking. This issue is addressed by constructing a large-scale high-definition human image dataset named PersonHD with multimodal auxiliary data.
Method
2
This study constructs a large-scale， high-resolution human image dataset called PersonHD. Compared with other datasets， this dataset has several advantages. 1） Higher image resolution： the cropped human images in PersonHD have a resolution of 1 520 × 880 pixels. 2） More diverse pose variations： the actions of the subjects are closer to real-life scenarios， introducing more fine-grained nonrigid deformation of the human body. 3） Larger image size. The PersonHD dataset contains 299 817 images from 100 different people in 4 000 videos. On the basis of the proposed PersonHD， this study further constructs two benchmarks and designs a practical high-resolution human image generation framework. Given that most existing works address human images with a resolution of 256 × 256 pixels， this study first establishes a low-resolution （256 × 256 pixels） benchmark for general evaluation， evaluates the performance of these methods on the PersonHD dataset， and further improves the performance of the state-of-the-art methods. This study also constructs a high-definition benchmark （512 × 512 pixels） to verify the performance of the state-of-the-art methods on the PersonHD dataset. These two benchmarks also enable this study to rigorously evaluate the performance of existing and future human pose transfer methods. In addition， this study proposes a practical framework to generate higher-resolution and higher-quality human images. In particular， this study first designs semantically enhanced partwise augmentation to solve the challenging overfitting problem in human image generation. A conditional upsampling module is then introduced for the generation and further refinement of high-resolution images.
Result
2
Compared with existing datasets， PersonHD has significant advantages in terms of higher image resolution， more diverse pose variance， and larger sample sizes. On the PersonHD dataset， experiments systematically evaluate the current representative pose-guided character image generation methods on two different resolution evaluation benchmarks and systematically validate the effectiveness of each module of the framework proposed in this study. The experiment used five indicators to quantitatively analyze the performance of the model， including the structure similarity index measure（SSIM）， Frechet inception distance（FID）， learned perceptual image patch similarity（LPIPS）， mask LPIPS， and percentage of correct keypoints with head-normalization（PCKh）. For low-resolution benchmarks， most current methods are designed for low-resolution images of size 256 × 256 pixels. The image size was adjusted to 256 × 256 pixels during the experiment to evaluate these methods on the PersonHD dataset. Moreover， PersonHD was split into two subsets， namely， a clean subset and a complex subset， to evaluate the processing ability of different models for different backgrounds. This method compares several of the latest methods on two subsets of PersonHD， including pose-attentional transfer network（PATN）， Must-GAN， Xing-GAN， pose-guided image synthesis and editing（PISE）， and semantic part-based generation network（SPGNet）. During the experiment， semantically enhanced partwise augmentation and one-shot-driven personalization were used to improve the performance of SPGNet as the baseline. The semantically enhanced partwise augmentation and one-shot driven personalization proposed in this research improve the performance of SPGNet in terms of multiple indicators， and the relevant modules of the framework significantly improve the model’s performance. For high-resolution benchmarks， given the limited work on pose-guided character image generation at high resolution， this study uses a conditional upsampling module to design the most advanced SPGNet model and further improves performance by using semantically enhanced partwise augmentation methods and one-shot-driven personalization. The experimental results indicate that the framework has good performance.
Conclusion
2
A large-scale high-resolution person image dataset called PersonHD， which contains 299 817 high-quality images， was developed. Compared with existing datasets， PersonHD has significant superiority in terms of higher image resolution， more diverse pose-variance， and larger scale samples. The high-definition character image generation benchmark dataset proposed in this article has the characteristics of a large scale and strong diversit
y of high-resolution data， which helps to comprehensively evaluate pose-guided character image generation algorithms. Comprehensive benchmarks were established， and extensive experimental evaluations were implemented on the basis of general low-definition protocols and the first proposed high-definition protocols， which could contribute to an important platform for analyzing recent state-of-the-art person image generation methods. A unified framework for high-definition person image generation， including semantically enhanced partwise augmentation and a conditional upsampling module， was also used. Both modules are flexible and can work separately in a plug-and-play manner. The dataset and code proposed in this work are available at
https://github.com/BraveGroup/PersonHD
https://github.com/BraveGroup/PersonHD
.
Albahar B ， Lu J W ， Yang J M ， Shu Z X ， Shechtman E and Huang J B . 2021 . Pose with style： detail-preserving pose-guided image synthesis with conditional StyleGAN . ACM Transactions on Graphics ， 40 （ 6 ）： # 218 ［ DOI： 10.1145/3478513.3480559 http://dx.doi.org/10.1145/3478513.3480559 ］
Andriluka M ， Pishchulin L ， Gehler P and Schiele B . 2014 . 2D human pose estimation： new benchmark and state of the art analysis // Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition . Columbus， USA ： IEEE： 3686 - 3693 ［ DOI： 10.1109/CVPR.2014.471 http://dx.doi.org/10.1109/CVPR.2014.471 ］
Cao Z ， Simon T ， Wei S E and Sheikh Y . 2017 . Realtime multi-person 2D pose estimation using part affinity fields // Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu， USA ： IEEE： 1302 - 1310 ［ DOI： 10.1109/CVPR.2017.143 http://dx.doi.org/10.1109/CVPR.2017.143 ］
Dong H Y ， Liang X D ， Shen X H ， Wang B C ， Lai H J ， Zhu J ， Hu Z T and Yin J . 2019 . Towards multi-pose guided virtual try-on network // Proceedings of 2019 IEEE/CVF International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 9025 - 9034 ［ DOI： 10.1109/ICCV.2019.00912 http://dx.doi.org/10.1109/ICCV.2019.00912 ］
Fu J L ， Li S K ， Jiang Y M ， Lin K Y ， Qian C ， C. Loy C C ， Wu W and Liu Z W . 2022 . StyleGAN-human： a data-centric odyssey of human generation // Proceedings of the 17th European Conference on Computer Vision . Tel Aviv， Israel ： Springer： 1 - 19 ［ DOI： 10.1007/978-3-031-19787-1_1 http://dx.doi.org/10.1007/978-3-031-19787-1_1 ］
Heusel M ， Ramsauer H ， Unterthiner T ， Nessler B and Hochreiter S . 2017 . GANs trained by a two time-scale update rule converge to a local Nash equilibrium // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach， USA ： Curran Associates Inc.： 6629 - 6640 ［ DOI： 10.5555/3295222.3295408 http://dx.doi.org/10.5555/3295222.3295408 ］
Isola P ， Zhu J Y ， Zhou T H and Efros A A . 2017 . Image-to-image translation with conditional adversarial networks // Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu， USA ： IEEE： 5967 - 5976 ［ DOI： 10.1109/CVPR.2017.632 http://dx.doi.org/10.1109/CVPR.2017.632 ］
Jiang Y M ， Chan K C K ， Wang X T ， Loy C C and Liu Z W . 2021 . Robust reference-based super-resolution via C 2 -matching // Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， USA ： IEEE： 2103 - 2112 ［ DOI： 10.1109/CVPR46437.2021.00214 http://dx.doi.org/10.1109/CVPR46437.2021.00214 ］
Karmakar A and Mishra D . 2019 . A robust pose transformational GAN for pose guided person image synthesis // Proceedings of the 7th National Conference on Computer Vision， Pattern Recognition， Image Processing， and Graphics . Hubballi， India ： Springer： 89 - 99 ［ DOI： 10.1007/978-981-15-8697-2_8 http://dx.doi.org/10.1007/978-981-15-8697-2_8 ］
Karras T ， Laine S ， Aittala M ， Hellsten J ， Lehtinen J and Aila T . 2020 . Analyzing and improving the image quality of styleGAN // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 8107 - 8116 ［ DOI： 10.1109/CVPR42600.2020.00813 http://dx.doi.org/10.1109/CVPR42600.2020.00813 ］
Khatun A ， Denman S ， Sridharan S and Fookes C . 2023 . Pose-driven attention-guided image generation for person re-identification . Pattern Recognition ， 137 ： # 109246 ［ DOI： 10.1016/j.patcog.2022.109246 http://dx.doi.org/10.1016/j.patcog.2022.109246 ］
Li J ， Yang J ， Wang L Y and Wang Y G . 2024 . Incorporating variational auto-encoder networks for text-driven generation of 3D motion human body . Journal of Image and Graphics ， 29 （ 5 ）： 1434 - 1446
李健 ， 杨钧 ， 王丽燕 ， 王永归 . 2024 . 融入变分自编码网络的文本生成三维运动人体 . 中国图象图形学报 ， 29 （ 5 ）： 1434 - 1446 ［ DOI： 10.11834/jig.230291 http://dx.doi.org/10.11834/jig.230291 ］
Li K ， Zhang J S ， Liu Y B ， Lai Y K and Dai Q H . 2020 . PoNA： pose-guided non-local attention for human pose transfer . IEEE Transactions on Image Processing ， 29 ： 9584 - 9599 ［ DOI： 10.1109/TIP.2020.3029455 http://dx.doi.org/10.1109/TIP.2020.3029455 ］
Li T J ， Zhang W ， Song R ， Li Z H ， Liu J ， Li X L and S J Lu . 2021 . PoT-GAN： pose transform GAN for person image synthesis . IEEE Transactions on Image Processing ， 30 ： 7677 - 7688 ［ DOI： 10.1109/TIP.2021.3104183 http://dx.doi.org/10.1109/TIP.2021.3104183 ］
Li Y N ， Huang C and Loy C C . 2019 . Dense intrinsic appearance flow for human pose transfer // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 3688 - 3697 ［ DOI： 10.1109/CVPR.2019.00381 http://dx.doi.org/10.1109/CVPR.2019.00381 ］
Liang X D ， Gong K ， Shen X H and Lin L . 2019 . Look into person： joint body parsing and pose estimation network and a new benchmark . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 41 （ 4 ）： 871 - 885 ［ DOI： 10.1109/TPAMI.2018.2820063 http://dx.doi.org/10.1109/TPAMI.2018.2820063 ］
Liu M C ， Yan X ， Wang C H and Wang K J . 2021 . Segmentation mask-guided person image generation . Applied Intelligence ， 51 （ 2 ）： 1161 - 1176 ［ DOI： 10.1007/s10489-020-01907-w http://dx.doi.org/10.1007/s10489-020-01907-w ］
Liu W ， Piao Z X ， Min J ， Luo W H ， Ma L and Gao S H . 2019 . Liquid warping GAN ： a unified framework for human motion imitation， appearance transfer and novel view synthesis// Proceedings of 2019 IEEE/CVF International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 5903 - 5912 ［ DOI： 10.1109/ICCV.2019.00600 http://dx.doi.org/10.1109/ICCV.2019.00600 ］
Liu W ， Piao Z X ， Tu Z ， Luo W H ， Ma L and Gao S H . 2022 . Liquid warping GAN with attention： a unified framework for human image synthesis . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 44 （ 9 ）： 5115 - 5133 ［ DOI： 10.1109/TPAMI.2021.3078270 http://dx.doi.org/10.1109/TPAMI.2021.3078270 ］
Liu Z W ， Luo P ， Qiu S ， Wang X G and Tang X O . 2016 . DeepFashion： powering robust clothes recognition and retrieval with rich annotations // Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas， USA ： IEEE： 1096 - 1104 ［ DOI： 10.1109/CVPR.2016.124 http://dx.doi.org/10.1109/CVPR.2016.124 ］
Ly Z Y ， Li X M ， Li X ， Li F ， Lin T W ， He D L and Zuo W M . 2021 . Learning semantic person image generation by region-adaptive normalization // Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， USA ： IEEE： 10801 - 10810 ［ DOI： 10.1109/CVPR46437.2021.01066 http://dx.doi.org/10.1109/CVPR46437.2021.01066 ］
Ma L Q ， Jia X ， Sun Q R ， Schiele B ， Tuytelaars T and Van Gool L . 2017 . Pose guided person image generation // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach， USA ： Curran Associates Inc.： 405 - 415
Ma L Y ， Huang K J ， Wei D X ， Ming Z Y and Shen H B . 2023 . FDA-GAN： flow-based dual attention GAN for human pose transfer . IEEE Transactions on Multimedia ， 25 ： 930 - 941 ［ DOI： 10.1109/TMM.2021.3134157 http://dx.doi.org/10.1109/TMM.2021.3134157 ］
Ma T X ， Peng B ， Wang W and Dong J . 2021 . Must-GAN： multi-level statistics transfer for self-driven person image generation // Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， USA ： IEEE： 13617 - 13626 ［ DOI： 10.1109/CVPR46437.2021.01341 http://dx.doi.org/10.1109/CVPR46437.2021.01341 ］
Men Y F ， Mao Y M ， Jiang Y N ， Ma W Y and Lian Z H . 2020 . Controllable person image synthesis with attribute-decomposed GAN // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 5083 - 5092 ［ DOI： 10.1109/CVPR42600.2020.00513 http://dx.doi.org/10.1109/CVPR42600.2020.00513 ］
Mirza M and Osindero S . 2014 . Conditional generative adversarial nets ［EB/OL］. ［ 2024-03-01 ］. https://arxiv.org/pdf/1411.1784.pdf https://arxiv.org/pdf/1411.1784.pdf
Pumarola A ， Agudo A ， Sanfeliu A and Moreno-Noguer F . 2018 . Unsupervised person image synthesis in arbitrary poses // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 8620 - 8628 ［ DOI： 10.1109/CVPR.2018.00899 http://dx.doi.org/10.1109/CVPR.2018.00899 ］
Qian X L ， Fu Y W ， Xiang T ， Wang W X ， Qiu J ， Wu Y ， Jiang Y G and Xue X Y . 2018 . Pose-normalized image generation for person re-identification // Proceedings of the 15th European Conference on Computer Vision . Munich， Germany ： Springer： 661 - 678 ［ DOI： 10.1007/978-3-030-01240-3_40 http://dx.doi.org/10.1007/978-3-030-01240-3_40 ］
Ren J ， Chai M L ， Woodford O J ， Olszewski K and Tulyakov S . 2021 . Flow guided transformable bottleneck networks for motion retargeting // Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， USA ： IEEE： 10790 - 10800 ［ DOI： 10.1109/CVPR46437.2021.01065 http://dx.doi.org/10.1109/CVPR46437.2021.01065 ］
Ren Y R ， Yu X M ， Chen J M ， Li T H and Li G . 2020 . Deep image spatial transformation for person image generation // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 7687 - 7696 ［ DOI： 10.1109/CVPR42600.2020.00771 http://dx.doi.org/10.1109/CVPR42600.2020.00771 ］
Roy P ， Bhattacharya S ， Ghosh S and Pal U . 2023 . Multi-scale attention guided pose transfer . Pattern Recognition ， 137 ： # 109315 ［ DOI： 10.1016/j.patcog.2023.109315 http://dx.doi.org/10.1016/j.patcog.2023.109315 ］
Siarohin A ， Sangineto E ， Lathuilière S and Sebe N . 2018 . Deformable GANs for pose-based human image generation // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 3408 - 3416 ［ DOI： 10.1109/CVPR.2018.00359 http://dx.doi.org/10.1109/CVPR.2018.00359 ］
Song S J ， Zhang W ， Liu J Y and Liu T . 2019 . Unsupervised person image generation with semantic parsing transformation // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 2352 - 2361 ［ DOI： 10.1109/CVPR.2019.00246 http://dx.doi.org/10.1109/CVPR.2019.00246 ］
Sun Y ， Ding J W ， Zhang Q and Deng Q Y . 2024 . Images super-resolution reconstruction of transposed self-attention with local feature enhancement . Journal of Image and Graphics ， 29 （ 4 ）： 908 - 921
孙阳 ， 丁建伟 ， 张琪 ， 邓琪瑶 . 2024 . 局部特征增强的转置自注意力图像超分辨率重建 . 中国图象图形学报 ， 29 （ 4 ）： 908 - 921 ［ DOI： 10.11834/jig.230320 http://dx.doi.org/10.11834/jig.230320 ］
Tang H ， Bai S ， Zhang L ， Torr P H S and Sebe N . 2020 . XingGAN for person image generation // Proceedings of the 16th European Conference on Computer Vision . Glasgow， UK ： Springer： 717 - 734 ［ DOI： 10.1007/978-3-030-58595-2_43 http://dx.doi.org/10.1007/978-3-030-58595-2_43 ］
Tang H ， Xu D ， Liu G W ， Wang W ， Sebe N and Yan Y . 2019 . Cycle in cycle generative adversarial networks for keypoint-guided image generation // Proceedings of the 27th ACM International Conference on Multimedia . Nice， France ： ACM： 2052 - 2060 ［ DOI： 10.1145/3343031.3350980 http://dx.doi.org/10.1145/3343031.3350980 ］
Wang T C ， Liu M Y ， Zhu J Y ， Tao A ， Kautz J and Catanzaro B . 2018 . High-resolution image synthesis and semantic manipulation with conditional GANs // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 8798 - 8807 ［ DOI： 10.1109/CVPR.2018.00917 http://dx.doi.org/10.1109/CVPR.2018.00917 ］
Wang Z ， Bovik A C ， Sheikh H R and Simoncelli E P . 2004 . Image quality assessment： from error visibility to structural similarity . IEEE Transactions on Image Processing ， 13 （ 4 ）： 600 - 612 ［ DOI： 10.1109/TIP.2003.819861 http://dx.doi.org/10.1109/TIP.2003.819861 ］
Xiong W ， Xiong C Y ， Gao Z R ， Chen W Q ， Zheng R H and Tian J W . 2023 . Image super-resolution with channel-attention-embedded Transformer . Journal of Image and Graphics ， 28 （ 12 ）： 3744 - 3757
熊巍 ， 熊承义 ， 高志荣 ， 陈文旗 ， 郑瑞华 ， 田金文 . 2023 . 通道注意力嵌入的Transformer图像超分辨率重构 . 中国图象图形学报 ， 28 （ 12 ）： 3744 - 3757 ［ DOI： 10.11834/jig.221033 http://dx.doi.org/10.11834/jig.221033 ］
Yang F Z ， Yang H ， Fu J L ， Lu H T and Guo B N . 2020a . Learning texture Transformer network for image super-resolution // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 5790 - 5799 ［ DOI： 10.1109/CVPR42600.2020.00583 http://dx.doi.org/10.1109/CVPR42600.2020.00583 ］
Yang H ， Zhang R M ， Guo X B ， Liu W ， Zuo W M and Luo P . 2020b . Towards photo-realistic virtual try-on by adaptively generating↔preserving image content // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 7847 - 7856 ［ DOI： 10.1109/CVPR42600.2020.00787 http://dx.doi.org/10.1109/CVPR42600.2020.00787 ］
Yoon J S ， Liu L J ， Golyanik V ， Sarkar K ， Park H S and Theobalt C . 2021 . Pose-guided human animation from a single image in the wild // Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， USA ： IEEE： 15034 - 15043 ［ DOI： 10.1109/CVPR46437.2021.01479 http://dx.doi.org/10.1109/CVPR46437.2021.01479 ］
Zhang J S ， Li K ， Lai Y K and Yang J Y . 2021 . PISE： person image synthesis and editing with decoupled GAN // Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， USA ： IEEE： 7978 - 7986 ［ DOI： 10.1109/CVPR46437.2021.00789 http://dx.doi.org/10.1109/CVPR46437.2021.00789 ］
Zhang P Z ， Yang L X ， Lai J H and Xie X H . 2022 . Exploring dual-task correlation for pose guided person image generation // Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， USA ： IEEE： 7703 - 7712 ［ DOI： 10.1109/CVPR52688.2022.00756 http://dx.doi.org/10.1109/CVPR52688.2022.00756 ］
Zhang R ， Isola P ， Efros A A ， Shechtman E and Wang O . 2018 . The unreasonable effectiveness of deep features as a perceptual metric // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 586 - 595 ［ DOI： 10.1109/CVPR.2018.00068 http://dx.doi.org/10.1109/CVPR.2018.00068 ］
Zhang Z F ， Wang Z W ， Lin Z and Qi H R . 2019 . Image super-resolution by neural texture transfer // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 7974 - 7983 ［ DOI： 10.1109/CVPR.2019.00817 http://dx.doi.org/10.1109/CVPR.2019.00817 ］
Zheng L ， Shen L Y ， Tian L ， Wang S J ， Wang J D and Tian Q . 2015 . Scalable person re-identification： a benchmark // Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago， Chile ： IEEE： 1116 - 1124 ［ DOI： 10.1109/ICCV.2015.133 http://dx.doi.org/10.1109/ICCV.2015.133 ］
Zhou X R ， Zhang B ， Zhang T ， Zhang P ， Bao J M ， Chen D ， Zhang Z F and Wen F . 2021 . CoCosNet v2： full-resolution correspondence learning for image translation // Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Nashville， USA ： IEEE： 11460 - 11470 ［ DOI： 10.1109/CVPR46437.2021.01130 http://dx.doi.org/10.1109/CVPR46437.2021.01130 ］
Zhu J Y ， Park T ， Isola P and Efros A A . 2017 . Unpaired image-to-image translation using cycle-consistent adversarial networks // Proceedings of 2017 IEEE International Conference on Computer Vision . Venice， Italy ： IEEE： 2242 - 2251 ［ DOI： 10.1109/ICCV.2017.244 http://dx.doi.org/10.1109/ICCV.2017.244 ］
Zhu Z ， Huang T T ， Shi B G ， Yu M ， Wang B F and Bai X . 2019 . Progressive pose attention transfer for person image generation // Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach， USA ： IEEE： 2342 - 2351 ［ DOI： 10.1109/CVPR.2019.00245 http://dx.doi.org/10.1109/CVPR.2019.00245 ］
相关文章
相关作者
相关机构
京公网安备11010802024621