Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914869315371008 |
|---|---|
| author | Luan, Tianyu Gao, Zhongpai Xie, Luyuan Sharma, Abhishek Ding, Hao Planche, Benjamin Zheng, Meng Lou, Ange Chen, Terrence Yuan, Junsong Wu, Ziyan |
| author_facet | Luan, Tianyu Gao, Zhongpai Xie, Luyuan Sharma, Abhishek Ding, Hao Planche, Benjamin Zheng, Meng Lou, Ange Chen, Terrence Yuan, Junsong Wu, Ziyan |
| contents | We introduce a novel bottom-up approach for human body mesh reconstruction, specifically designed to address the challenges posed by partial visibility and occlusion in input images. Traditional top-down methods, relying on whole-body parametric models like SMPL, falter when only a small part of the human is visible, as they require visibility of most of the human body for accurate mesh reconstruction. To overcome this limitation, our method employs a "Divide and Fuse (D&F)" strategy, reconstructing human body parts independently before fusing them, thereby ensuring robustness against occlusions. We design Human Part Parametric Models (HPPM) that independently reconstruct the mesh from a few shape and global-location parameters, without inter-part dependency. A specially designed fusion module then seamlessly integrates the reconstructed parts, even when only a few are visible. We harness a large volume of ground-truth SMPL data to train our parametric mesh models. To facilitate the training and evaluation of our method, we have established benchmark datasets featuring images of partially visible humans with HPPM annotations. Our experiments, conducted on these benchmark datasets, demonstrate the effectiveness of our D&F method, particularly in scenarios with substantial invisibility, where traditional approaches struggle to maintain reconstruction quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09694 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images Luan, Tianyu Gao, Zhongpai Xie, Luyuan Sharma, Abhishek Ding, Hao Planche, Benjamin Zheng, Meng Lou, Ange Chen, Terrence Yuan, Junsong Wu, Ziyan Computer Vision and Pattern Recognition We introduce a novel bottom-up approach for human body mesh reconstruction, specifically designed to address the challenges posed by partial visibility and occlusion in input images. Traditional top-down methods, relying on whole-body parametric models like SMPL, falter when only a small part of the human is visible, as they require visibility of most of the human body for accurate mesh reconstruction. To overcome this limitation, our method employs a "Divide and Fuse (D&F)" strategy, reconstructing human body parts independently before fusing them, thereby ensuring robustness against occlusions. We design Human Part Parametric Models (HPPM) that independently reconstruct the mesh from a few shape and global-location parameters, without inter-part dependency. A specially designed fusion module then seamlessly integrates the reconstructed parts, even when only a few are visible. We harness a large volume of ground-truth SMPL data to train our parametric mesh models. To facilitate the training and evaluation of our method, we have established benchmark datasets featuring images of partially visible humans with HPPM annotations. Our experiments, conducted on these benchmark datasets, demonstrate the effectiveness of our D&F method, particularly in scenarios with substantial invisibility, where traditional approaches struggle to maintain reconstruction quality. |
| title | Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.09694 |