Efficient participating media rendering with differentiable regularization  

作　　者：Wenshi Wu Beibei Wang Milos Hasan Lei Zhang Zhong Jin Ling-Qi Yan 

机构地区：[1]School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China [2]Adobe Research,San Jose,CA 95110-2704,USA [3]Department of Computing,Hong Kong Polytechnic,University,Hong Kong 999077,China [4]Department of ComjouterScience,University of California Santa Barbara,CA 93106,USA.

出　　处：《Computational Visual Media》2024年第5期937-948,共12页计算可视媒体（英文版）

基　　金：supported by the National Natural Science Foundation of China under Grant No.62172220。

摘　　要：Highly scattering media,such as milk,skin,and clouds,are common in the real world.Rendering participating media is challenging,especially for highorder scattering dominant media,because the light may undergo a large number of scattering events before leaving the surface.Monte Carlo-based methods typically require a long time to produce noise-free results.Based on the observation that low-albedo media contain less noise than high-albedo media,we propose reducing the variance of the rendered results using differentiable regularization.We first render an image with low-albedo participating media together with the gradient with respect to the albedo,and then predict the final rendered image with a low-albedo image and gradient image via a novel prediction function.To achieve high quality,we also consider the gradients of neighboring frames to provide a noise-free gradient image.Ultimately,our method can produce results with much less overall eror than equal-time path tracing methods.

关 键 词：participating media differentiable regularization differentiable rendering volumetric path tracing temporal denoising 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]