A detail preserving neural network model for Monte Carlo denoising

作     者：Weiheng Lin Beibei Wang Lu Wang Nicolas Holzschuch Weiheng Lin;Beibei Wang;Lu Wang;Nicolas Holzschuch

作者机构：School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing210094China School of Computer Science and TechnologyShandong UniversityJinan250100China Univ.Grenoble-AlpesInriaCNRSGrenoble INPLJK38000GrenobleFrance 

出 版 物：《Computational Visual Media》 (计算可视媒体（英文版）)

年 卷 期：2020年第6卷第2期

页      面：157-168页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：deep learning light transport covariance perceptual loss Monte Carlo denoising 

摘      要：Monte Carlo based methods such as path tracing are widely used in movie production. To achieve low noise, they require many samples per pixel,resulting in long rendering time. To reduce the cost,one solution is Monte Carlo denoising, which renders the image with fewer samples per pixel(as little as128) and then denoises the resulting image. Many Monte Carlo denoising methods rely on deep learning:they use convolutional neural networks to learn the relationship between noisy images and reference images,using auxiliary features such as position and normal together with image color as inputs. The network predicts kernels which are then applied to the noisy input. These methods show powerful denoising ability,but tend to lose geometric or lighting details and to blur sharp features during *** this paper, we solve this issue by proposing a novel network structure, a new input feature—light transport covariance from path space—and an improved loss function. Our network separates feature buffers from the color buffer to enhance detail effects. The features are extracted separately and then integrated into a shallow kernel predictor. Our loss function considers perceptual loss, which also improves detail *** addition, we use a light transport covariance feature in path space as one of the features, which helps to preserve illumination details. Our method denoises Monte Carlo path traced images while preserving details much better than previous methods.