Search Results for author:
Found 9 papers, 4 papers with code
Generative Detail Enhancement for Physically Based Materials
The details it generates are then backpropagated from the enhanced images to the material parameters via inverse differentiable rendering.
DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Classic physically-based rendering (PBR) accurately simulates the light transport, but relies on precise scene representations--explicit 3D geometry, high-quality material properties, and lighting conditions--that are often impractical to obtain in real-world scenarios.
Edify 3D: Scalable High-Quality 3D Asset Generation
We introduce Edify 3D, an advanced solution designed for high-quality 3D asset generation.
Flexible Isosurface Extraction for Gradient-Based Mesh Optimization
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 modeling, and inverse physics.
Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion.
Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes
Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion.
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising
Unfortunately, Monte Carlo integration provides estimates with significant noise, even at large sample counts, which makes gradient-based inverse rendering very challenging.
Ranked #1 on
Surface Normals Estimation
on Stanford-ORB
Extracting Triangular 3D Models, Materials, and Lighting From Images
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
Ranked #2 on
Depth Prediction
on Stanford-ORB
Noise2Noise: Learning Image Restoration without Clean Data
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption.
