PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910906085015552 |
|---|---|
| author | Bao, Jingzhi Chen, Guanying Cui, Shuguang |
| author_facet | Bao, Jingzhi Chen, Guanying Cui, Shuguang |
| contents | This paper addresses the problem of inverse rendering from photometric images. Existing approaches for this problem suffer from the effects of self-shadows, inter-reflections, and lack of constraints on the surface reflectance, leading to inaccurate decomposition of reflectance and illumination due to the ill-posed nature of inverse rendering. In this work, we propose a new method for neural inverse rendering. Our method jointly optimizes the light source position to account for the self-shadows in images, and computes indirect illumination using a differentiable rendering layer and an importance sampling strategy. To enhance surface reflectance decomposition, we introduce a new regularization by distilling DINO features to foster accurate and consistent material decomposition. Extensive experiments on synthetic and real datasets demonstrate that our method outperforms the state-of-the-art methods in reflectance decomposition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06828 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization Bao, Jingzhi Chen, Guanying Cui, Shuguang Computer Vision and Pattern Recognition This paper addresses the problem of inverse rendering from photometric images. Existing approaches for this problem suffer from the effects of self-shadows, inter-reflections, and lack of constraints on the surface reflectance, leading to inaccurate decomposition of reflectance and illumination due to the ill-posed nature of inverse rendering. In this work, we propose a new method for neural inverse rendering. Our method jointly optimizes the light source position to account for the self-shadows in images, and computes indirect illumination using a differentiable rendering layer and an importance sampling strategy. To enhance surface reflectance decomposition, we introduce a new regularization by distilling DINO features to foster accurate and consistent material decomposition. Extensive experiments on synthetic and real datasets demonstrate that our method outperforms the state-of-the-art methods in reflectance decomposition. |
| title | PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.06828 |