Differentiable Convex Polyhedra Optimization from Multi-view 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_ | 1866929430600876032 |
|---|---|
| author | Ren, Daxuan Mei, Haiyi Shi, Hezi Zheng, Jianmin Cai, Jianfei Yang, Lei |
| author_facet | Ren, Daxuan Mei, Haiyi Shi, Hezi Zheng, Jianmin Cai, Jianfei Yang, Lei |
| contents | This paper presents a novel approach for the differentiable rendering of convex polyhedra, addressing the limitations of recent methods that rely on implicit field supervision. Our technique introduces a strategy that combines non-differentiable computation of hyperplane intersection through duality transform with differentiable optimization for vertex positioning with three-plane intersection, enabling gradient-based optimization without the need for 3D implicit fields. This allows for efficient shape representation across a range of applications, from shape parsing to compact mesh reconstruction. This work not only overcomes the challenges of previous approaches but also sets a new standard for representing shapes with convex polyhedra. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15686 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Differentiable Convex Polyhedra Optimization from Multi-view Images Ren, Daxuan Mei, Haiyi Shi, Hezi Zheng, Jianmin Cai, Jianfei Yang, Lei Graphics Computer Vision and Pattern Recognition This paper presents a novel approach for the differentiable rendering of convex polyhedra, addressing the limitations of recent methods that rely on implicit field supervision. Our technique introduces a strategy that combines non-differentiable computation of hyperplane intersection through duality transform with differentiable optimization for vertex positioning with three-plane intersection, enabling gradient-based optimization without the need for 3D implicit fields. This allows for efficient shape representation across a range of applications, from shape parsing to compact mesh reconstruction. This work not only overcomes the challenges of previous approaches but also sets a new standard for representing shapes with convex polyhedra. |
| title | Differentiable Convex Polyhedra Optimization from Multi-view Images |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.15686 |