Differentiable Point-based Inverse Rendering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chung, Hoon-Gyu, Choi, Seokjun, Baek, Seung-Hwan
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913280770965504
author Chung, Hoon-Gyu
Choi, Seokjun
Baek, Seung-Hwan
author_facet Chung, Hoon-Gyu
Choi, Seokjun
Baek, Seung-Hwan
contents We present differentiable point-based inverse rendering, DPIR, an analysis-by-synthesis method that processes images captured under diverse illuminations to estimate shape and spatially-varying BRDF. To this end, we adopt point-based rendering, eliminating the need for multiple samplings per ray, typical of volumetric rendering, thus significantly enhancing the speed of inverse rendering. To realize this idea, we devise a hybrid point-volumetric representation for geometry and a regularized basis-BRDF representation for reflectance. The hybrid geometric representation enables fast rendering through point-based splatting while retaining the geometric details and stability inherent to SDF-based representations. The regularized basis-BRDF mitigates the ill-posedness of inverse rendering stemming from limited light-view angular samples. We also propose an efficient shadow detection method using point-based shadow map rendering. Our extensive evaluations demonstrate that DPIR outperforms prior works in terms of reconstruction accuracy, computational efficiency, and memory footprint. Furthermore, our explicit point-based representation and rendering enables intuitive geometry and reflectance editing.
format Preprint
id arxiv_https___arxiv_org_abs_2312_02480
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Differentiable Point-based Inverse Rendering
Chung, Hoon-Gyu
Choi, Seokjun
Baek, Seung-Hwan
Computer Vision and Pattern Recognition
We present differentiable point-based inverse rendering, DPIR, an analysis-by-synthesis method that processes images captured under diverse illuminations to estimate shape and spatially-varying BRDF. To this end, we adopt point-based rendering, eliminating the need for multiple samplings per ray, typical of volumetric rendering, thus significantly enhancing the speed of inverse rendering. To realize this idea, we devise a hybrid point-volumetric representation for geometry and a regularized basis-BRDF representation for reflectance. The hybrid geometric representation enables fast rendering through point-based splatting while retaining the geometric details and stability inherent to SDF-based representations. The regularized basis-BRDF mitigates the ill-posedness of inverse rendering stemming from limited light-view angular samples. We also propose an efficient shadow detection method using point-based shadow map rendering. Our extensive evaluations demonstrate that DPIR outperforms prior works in terms of reconstruction accuracy, computational efficiency, and memory footprint. Furthermore, our explicit point-based representation and rendering enables intuitive geometry and reflectance editing.
title Differentiable Point-based Inverse Rendering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.02480