Computer Graphics Laboratory ETH Zurich


Deep Compositional Denoising for High-quality Monte Carlo Rendering

X. Zhang, M. Manzi, T. Vogels, H. Dahlberg, M. Gross, M. Papas

Proceedings of Eurographics Symposium on Rendering (EGSR) (Vienna, Austria, June 29 -- July 2, 2021), Computer Graphics Forum, vol. 40, no. 4, 2021, pp. 1-13


We 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.

Additional resources:


Download Paper
Download Paper
[PDF suppl.]
Download Paper