Deep Compositional Denoising for High‐quality Monte Carlo Rendering

doi:10.1111/cgf.14337

Deep Compositional Denoising for High‐quality Monte Carlo Rendering

2021-07-15

0

PRE

AI

DOI：10.1111/cgf.14337

原文链接

原文求助

摘要

En 中文

AbstractWe propose a deep‐learning method for automatically decomposing noisy Monte Carlo renderings into components that kernel‐predicting denoisers can denoise more effectively. In our model, a neural decomposition module learns to predict noisy components and corresponding feature maps, which are consecutively reconstructed by a denoising module. The components are predicted based on statistics aggregated at the pixel level by the renderer. Denoising these components individually allows the use of per‐component kernels that adapt to each component's noisy signal characteristics. Experimentally, we show that the proposed decomposition module consistently improves the denoising quality of current state‐of‐the‐art kernel‐predicting denoisers on large‐scale academic and production datasets.

Deep Compositional Denoising for High‐quality Monte Carlo Rendering

摘要

AI总结

期刊

机构

引用论文