Path Tracing Denoising Based on SURE Adaptive Sampling and Neural Network

• Published in: IEEE access Vol. 8; pp. 116336 - 116349
• Main Authors: Xing, Qiwei, Chen, Chunyi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive sampling; Algorithms; denoising; Feature extraction; Image color analysis; Image quality; Image reconstruction; MLPs network; Multilayer perceptrons; Neural networks; Noise; Noise level; Noise levels; Noise reduction; Numerical methods; Parameters; path tracing; Pixels; Rendering (computer graphics); SURE estimator; Tracing
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2999891

A novel reconstruction algorithm is presented to address the noise artifacts of path tracing. SURE (Stein's unbiased risk estimator) is adopted to estimate the noise level per pixel that guides adaptive sampling process. Modified MLPs (multilayer perceptron) network is used to predict the optimal reconstruction parameters. In sampling stage, coarse samples are firstly generated. Then each noise level is estimated with SURE. Additional samples are distributed to the pixels with high noise level. Next, we extract a few features from the results of adaptive sampling used for the subsequent reconstruction stage. In reconstruction stage, modified MLPs network is adopted to model a complex relationship between extracted features and optimal reconstruction parameters. An anisotropic filter is used to reconstruct the final images with the parameters predicted by neural networks. Compared to the state-of-the-art methods, experiment results demonstrate that our algorithm performs better than other methods in numerical error and visual image quality.