Affiliation:
1. University of California, Santa Barbara, Santa Barbara
2. University of California, San Diego and NVIDIA
3. University of California, San Diego
4. University of California, Santa Barbara
Abstract
In Computer Graphics, the two main approaches to rendering and visibility involve ray tracing and rasterization. However, a limitation of both approaches is that they essentially use point sampling. This is the source of noise and aliasing, and also leads to significant difficulties for differentiable rendering. In this work, we present a new rendering method, which we call vectorization, that computes 2D point-to-region integrals analytically, thus eliminating point sampling in the 2D integration domain such as for pixel footprints and area lights. Our vectorization revisits the concept of beam tracing, and handles the hidden surface removal problem robustly and accurately. That is, for each intersecting triangle inserted into the viewport of a beam in an arbitrary order, we are able to maintain all the visible regions formed by intersections and occlusions, thanks to our Visibility Bounding Volume Hierarchy structure. As a result, our vectorization produces perfectly anti-aliased visibility, accurate and analytic shading and shadows, and most important, fast and noise-free gradients with Automatic Differentiation or Finite Differences that directly enables differentiable rendering without any changes to our rendering pipeline. Our results are inherently high-quality and noise-free, and our gradients are one to two orders of magnitude faster than those computed with existing differentiable rendering methods.
Funder
NVIDIA Fellowship
Ronald L. Graham Chair
UC San Diego Center for Visual Computing
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Graphics and Computer-Aided Design
Cited by
12 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Projective Sampling for Differentiable Rendering of Geometry;ACM Transactions on Graphics;2023-12-05
2. A Differentiable Image Source Model for Room Acoustics Optimization;2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA);2023-10-22
3. Differentiable Heightfield Path Tracing with Accelerated Discontinuities;Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings;2023-07-23
4. Neural directional distance field object representation for uni-directional path-traced rendering;2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT);2023-07-06
5. Differentiable Shadow Mapping for Efficient Inverse Graphics;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06