Direct May Not Be the Best: An Incremental Evolution View of Pose Generation
Abstract: Pose diversity is an inherent representative characteristic of 2D images. Due to the 3D to 2D projection mechanism, there is evident content discrepancy among distinct pose images. This is the main obstacle bothering pose transformation related researches. To deal with this challenge, we propose a fine-grained incremental evolution centered pose generation framework, rather than traditional direct one-to-one in a rush. Since proposed approach actually bypasses the theoretical difficulty of directly modeling dramatic non-linear variation, the incurred content distortion and blurring could be effectively constrained, at the same time the various individual pose details, especially clothes texture, could be precisely maintained. In order to systematically guide the evolution course, both global and incremental evolution constraints are elaborately designed and merged into the overall framework. And a novel triple-path knowledge fusion structure is worked out to take full advantage of all available valuable knowledge to conduct high-quality pose synthesis. In addition, our framework could generate a series of valuable byproducts, namely the various intermediate poses. Extensive experiments have been conducted to verify the effectiveness of the proposed approach. Code is available at https://github.com/Xiaofei-CN/Incremental-Evolution-Pose-Generation.
- Person Image Synthesis via Denoising Diffusion Model. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5968–5976.
- Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7291–7299.
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications. IEEE Transactions on Knowledge and Data Engineering, 35(4): 3313–3332.
- Effective Face Frontalization in Unconstrained Images. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4295–4304.
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Proceedings of Advances in Neural Information Processing Systems (NeurIPS), volume 30.
- Arbitrary Style Transfer in Real-Time With Adaptive Instance Normalization. In Proceedings of IEEE International Conference on Computer Vision (ICCV), 1501–1510.
- Image fine-grained inpainting. arXiv preprint arXiv:2002.02609.
- Pose-Driven Attention-Guided Image Generation for Person Re-Identification. Pattern Recognition, 137: 109246.
- Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980.
- Frontal Face Synthesizing According to Multiple Non-Frontal Inputs and Its Application in Face Recognition. Neurocomputing, 91: 77–85.
- SPMPG: Robust Person Image Generation with Semantic Parsing Map. In Proceedings of IEEE International Conference on Image Processing (ICIP), 1364–1368.
- Look into Person: Joint Body Parsing & Pose Estimation Network and a New Benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(4): 871–885.
- Learning Semantic Person Image Generation by Region-Adaptive Normalization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10801–10810.
- Controllable Person Image Synthesis with Attribute-Decomposed GAN. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5083–5092.
- Multi-Scale Attention Guided Pose Transfer. Pattern Recognition, 137: 109315.
- Personalized Age Progression with Aging Dictionary. In Proceedings of IEEE International Conference on Computer Vision (ICCV), 3970–3978.
- XingGAN for Person Image Generation. In Proceedings of European Conference on Computer Vision (ECCV), 717–734.
- Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis. International Journal of Computer Vision, 131(3): 644–658.
- MoCoGAN: Decomposing Motion and Content for Video Generation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1526–1535.
- Attention is All you Need. In Proceedings of Advances in Neural Information Processing Systems (NeurIPS), volume 30.
- Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 13(4): 600–612.
- DwNet: Dense Warp-Based Network for Pose-Guided Human Video Generation. In Proceedings of British Machine Vision Conference (BMVC), 205.1–205.13.
- PISE: Person Image Synthesis and Editing with Decoupled GAN. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7978–7986.
- Human Pose Transfer by Adaptive Hierarchical Deformation. Computer Graphics Forum, 39(7): 325–337.
- Exploring Dual-Task Correlation for Pose Guided Person Image Generation. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7703–7712.
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 586–595.
- Cross attention based style distribution for controllable person image synthesis. In Proceedings of European Conference on Computer Vision (ECCV), 161–178.
- Progressive Pose Attention Transfer for Person Image Generation. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2342–2351.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
