PhySG: Inverse Rendering with Spherical Gaussians for Physics-Based Material Editing and Relighting

Abstract

We present an end-to-end inverse rendering pipeline that includes a fully differentiable renderer, and can reconstruct geometry, materials, and illumination from scratch from a set of images. Our rendering framework represents specular BRDFs and environmental illumination using mixtures of spherical Gaussians, and represents geometry as a signed distance function parameterized as a Multi-Layer Perceptron. The use of spherical Gaussians allows us to efficiently solve for approximate light transport, and our method works on scenes with challenging non-Lambertian reflectance captured under natural, static illumination. We demonstrate, with both synthetic and real data, that our reconstruction not only can render novel viewpoints, but also enables physics-based appearance editing of materials and illumination.

Cite

Text

Zhang et al. "PhySG: Inverse Rendering with Spherical Gaussians for Physics-Based Material Editing and Relighting." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00541

Markdown

[Zhang et al. "PhySG: Inverse Rendering with Spherical Gaussians for Physics-Based Material Editing and Relighting." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/zhang2021cvpr-physg/) doi:10.1109/CVPR46437.2021.00541

BibTeX

@inproceedings{zhang2021cvpr-physg,
  title     = {{PhySG: Inverse Rendering with Spherical Gaussians for Physics-Based Material Editing and Relighting}},
  author    = {Zhang, Kai and Luan, Fujun and Wang, Qianqian and Bala, Kavita and Snavely, Noah},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {5453-5462},
  doi       = {10.1109/CVPR46437.2021.00541},
  url       = {https://mlanthology.org/cvpr/2021/zhang2021cvpr-physg/}
}