A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis
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_ | 1866912030965891072 |
|---|---|
| author | Poirier-Ginter, Yohan Gauthier, Alban Philip, Julien Lalonde, Jean-Francois Drettakis, George |
| author_facet | Poirier-Ginter, Yohan Gauthier, Alban Philip, Julien Lalonde, Jean-Francois Drettakis, George |
| contents | Relighting radiance fields is severely underconstrained for multi-view data, which is most often captured under a single illumination condition; It is especially hard for full scenes containing multiple objects. We introduce a method to create relightable radiance fields using such single-illumination data by exploiting priors extracted from 2D image diffusion models. We first fine-tune a 2D diffusion model on a multi-illumination dataset conditioned by light direction, allowing us to augment a single-illumination capture into a realistic -- but possibly inconsistent -- multi-illumination dataset from directly defined light directions. We use this augmented data to create a relightable radiance field represented by 3D Gaussian splats. To allow direct control of light direction for low-frequency lighting, we represent appearance with a multi-layer perceptron parameterized on light direction. To enforce multi-view consistency and overcome inaccuracies we optimize a per-image auxiliary feature vector. We show results on synthetic and real multi-view data under single illumination, demonstrating that our method successfully exploits 2D diffusion model priors to allow realistic 3D relighting for complete scenes. Project site https://repo-sam.inria.fr/fungraph/generative-radiance-field-relighting/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08947 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis Poirier-Ginter, Yohan Gauthier, Alban Philip, Julien Lalonde, Jean-Francois Drettakis, George Computer Vision and Pattern Recognition Graphics I.3; I.4 Relighting radiance fields is severely underconstrained for multi-view data, which is most often captured under a single illumination condition; It is especially hard for full scenes containing multiple objects. We introduce a method to create relightable radiance fields using such single-illumination data by exploiting priors extracted from 2D image diffusion models. We first fine-tune a 2D diffusion model on a multi-illumination dataset conditioned by light direction, allowing us to augment a single-illumination capture into a realistic -- but possibly inconsistent -- multi-illumination dataset from directly defined light directions. We use this augmented data to create a relightable radiance field represented by 3D Gaussian splats. To allow direct control of light direction for low-frequency lighting, we represent appearance with a multi-layer perceptron parameterized on light direction. To enforce multi-view consistency and overcome inaccuracies we optimize a per-image auxiliary feature vector. We show results on synthetic and real multi-view data under single illumination, demonstrating that our method successfully exploits 2D diffusion model priors to allow realistic 3D relighting for complete scenes. Project site https://repo-sam.inria.fr/fungraph/generative-radiance-field-relighting/ |
| title | A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis |
| topic | Computer Vision and Pattern Recognition Graphics I.3; I.4 |
| url | https://arxiv.org/abs/2409.08947 |