Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2401.08930 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908709403230208 |
|---|---|
| author | Ji, Haorui Li, Hongdong |
| author_facet | Ji, Haorui Li, Hongdong |
| contents | Diffusion models have demonstrated impressive capabilities in modeling complex data distributions and are increasingly applied in various generative tasks. In this work, we propose Pose Analysis by Diffusion Synthesis PADS, a unified generative modeling framework for 3D human pose analysis. PADS first learns a task-agnostic 3D pose prior via unconditional diffusion synthesis and then performs training-free adaptation to a wide range of pose analysis tasks, including 3D pose estimation, denoising, completion, etc., through a posterior sampling scheme. By formulating each task as an inverse problem with a known forward operator, PADS injects task-specific constraints during inference while keeping the pose prior fixed. This plug-and-play framework removes the need for task-specific supervision or retraining, offering flexibility and scalability across diverse conditions. Extensive experiments on different benchmarks showcase the superior performance against both learning-based and optimization-based baselines, demonstrating the effectiveness and generalization capability of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08930 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modeling Ji, Haorui Li, Hongdong Computer Vision and Pattern Recognition Artificial Intelligence Diffusion models have demonstrated impressive capabilities in modeling complex data distributions and are increasingly applied in various generative tasks. In this work, we propose Pose Analysis by Diffusion Synthesis PADS, a unified generative modeling framework for 3D human pose analysis. PADS first learns a task-agnostic 3D pose prior via unconditional diffusion synthesis and then performs training-free adaptation to a wide range of pose analysis tasks, including 3D pose estimation, denoising, completion, etc., through a posterior sampling scheme. By formulating each task as an inverse problem with a known forward operator, PADS injects task-specific constraints during inference while keeping the pose prior fixed. This plug-and-play framework removes the need for task-specific supervision or retraining, offering flexibility and scalability across diverse conditions. Extensive experiments on different benchmarks showcase the superior performance against both learning-based and optimization-based baselines, demonstrating the effectiveness and generalization capability of our method. |
| title | PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative Modeling |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.08930 |