3 Hits in 2.2 sec

Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition [article]

Mark Boss, Varun Jampani, Raphael Braun, Ce Liu, Jonathan T. Barron, Hendrik P.A. Lensch
2021 arXiv   pre-print
Our key technique is a novel illumination integration network called Neural-PIL that replaces a costly illumination integral operation in the rendering with a simple network query.  ...  Project page:  ...  In contrast, our Neural-PIL is an MLP that directly produces pre-integrated light required for the rendering.  ... 
arXiv:2110.14373v1 fatcat:vg5s62ydwnffzivbyrqdu2g5tu

Extracting Triangular 3D Models, Materials, and Lighting From Images [article]

Jacob Munkberg, Jon Hasselgren, Tianchang Shen, Jun Gao, Wenzheng Chen, Alex Evans, Thomas Müller, Sanja Fidler
2022 arXiv   pre-print
We present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.  ...  Finally, we introduce a differentiable formulation of the split sum approximation of environment lighting to efficiently recover all-frequency lighting.  ...  In contrast, we propose a differentiable split sum lighting model, also adopted by the concurrent work Neural-PIL [6] .  ... 
arXiv:2111.12503v3 fatcat:pnd3yiexwvcqlkgxbebcwadlki

NeROIC: Neural Rendering of Objects from Online Image Collections [article]

Zhengfei Kuang, Kyle Olszewski, Menglei Chai, Zeng Huang, Panos Achlioptas, Sergey Tulyakov
Extensive evaluations and comparisons demonstrate the advantages of our approach in capturing high-quality geometry and appearance properties useful for rendering applications.  ...  Using a multi-stage approach extending neural radiance fields, we first infer the surface geometry and refine the coarsely estimated initial camera parameters, while leveraging coarse foreground object  ...  We will release our code, pre-trained models, and training datasets upon publication to facilitate further research effort in this area. Related Work Neural Rendering for Novel View Synthesis.  ... 
doi:10.48550/arxiv.2201.02533 fatcat:ymyxxmpk2vfppfbzcuvhaozmda