This work considers gradient-based mesh optimization, where we iteratively optimize for a 3D surface mesh by representing it as the isosurface of a scalar field, an increasingly common paradigm in applications including photogrammetry, generative …
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion. Recent NeRF based methods achieve impressive fidelity of 3D reconstruction, but bake the …
Recent advances in differentiable rendering have enabled high-quality reconstruction of 3D scenes from multi-view images. Most methods rely on simple rendering algorithms: pre-filtered direct lighting or learned representations of irradiance. We show …
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations. Unlike recent multi-view reconstruction approaches, which typically produce entangled 3D representations encoded in neural …
Recent work by Bitterli et al. introduced a real-time, many-light algorithm for rendering dynamic direct illumination from millions of lights by iteratively applying resampled importance sampling using weighted reservoir sampling. While enabling new …
We present a suite of techniques for jointly optimizing triangle meshes and shading models to match the appearance of reference scenes. This capability has a number of uses, including appearance-preserving simplification of extremely complex assets, …
We provide three analytical fits to the CIE x, y, and z color matching curves, commonly used in predictive and spectral renderers as an intermediate between light spectra and RGB colors. Any can replace the standard CIE curves, which come tabulated. …