Get 3D shape even with changing light using view-dependence normalization with VDN-NeRF
Get 3D shape even with changing light using view-dependence normalization with VDN-NeRF
VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization
arXiv paper abstract https://arxiv.org/abs/2303.17968
arXiv PDF paper https://arxiv.org/pdf/2303.17968.pdf
… propose VDN-NeRF, a method to train neural radiance fields (NeRFs) for better geometry under non-Lambertian surface and dynamic lighting conditions that cause significant variation in the radiance of a point when viewed from different angles.
Instead of explicitly modeling the underlying factors that result in the view-dependent phenomenon, which could be complex yet not inclusive, … develop a simple and effective technique that normalizes the view-dependence by distilling invariant information already encoded in the learned NeRFs.
… then jointly train NeRFs for view synthesis with view-dependence normalization to attain quality geometry.
… show that even though shape-radiance ambiguity is inevitable, the proposed normalization can minimize its effect on geometry, which essentially aligns the optimal capacity needed for explaining view-dependent variations.
… method applies to various baselines and significantly improves geometry without changing the volume rendering pipeline, even if the data is captured under a moving light source …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
