Surface reconstruction even when occlusion by using density with volume rendering with NeuS
Surface reconstruction even when occlusion by using density with volume rendering with NeuS
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
arXiv paper abstract https://arxiv.org/abs/2106.10689
arXiv PDF paper https://arxiv.org/pdf/2106.10689.pdf
GitHub https://github.com/Totoro97/NeuS
… present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs.
… neural surface reconstruction approaches, such as DVR and IDR, require foreground mask as supervision … struggle with … objects with severe self-occlusion or thin structures.
… neural methods for novel view synthesis, such as NeRF … use volume rendering … However, extracting high-quality surfaces … is difficult because there are not sufficient surface constraints in the representation.
In NeuS, … represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation.
… conventional volume rendering method causes inherent geometric errors (i.e. bias) for surface reconstruction, and therefore propose a new formulation that is free of bias
… NeuS outperforms the state-of-the-arts in high-quality surface reconstruction, especially for objects and scenes with complex structures and self-occlusion.
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
