LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911828489011200 |
|---|---|
| author | Wang, Xuecan Xiao, Shibang Liang, Xiaohui |
| author_facet | Wang, Xuecan Xiao, Shibang Liang, Xiaohui |
| contents | We present a lightweight solution for estimating spatially-coherent indoor lighting from a single RGB image. Previous methods for estimating illumination using volumetric representations have overlooked the sparse distribution of light sources in space, necessitating substantial memory and computational resources for achieving high-quality results. We introduce a unified, voxel octree-based illumination estimation framework to produce 3D spatially-coherent lighting. Additionally, a differentiable voxel octree cone tracing rendering layer is proposed to eliminate regular volumetric representation throughout the entire process and ensure the retention of features across different frequency domains. This reduction significantly decreases spatial usage and required floating-point operations without substantially compromising precision. Experimental results demonstrate that our approach achieves high-quality coherent estimation with minimal cost compared to previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03925 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation Wang, Xuecan Xiao, Shibang Liang, Xiaohui Computer Vision and Pattern Recognition We present a lightweight solution for estimating spatially-coherent indoor lighting from a single RGB image. Previous methods for estimating illumination using volumetric representations have overlooked the sparse distribution of light sources in space, necessitating substantial memory and computational resources for achieving high-quality results. We introduce a unified, voxel octree-based illumination estimation framework to produce 3D spatially-coherent lighting. Additionally, a differentiable voxel octree cone tracing rendering layer is proposed to eliminate regular volumetric representation throughout the entire process and ensure the retention of features across different frequency domains. This reduction significantly decreases spatial usage and required floating-point operations without substantially compromising precision. Experimental results demonstrate that our approach achieves high-quality coherent estimation with minimal cost compared to previous methods. |
| title | LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.03925 |