Learned Denoising

Computer Graphics · Denoising · 2017 · also: OIDN, OptiX denoiser · neural-denoising.yaml

Trains a network on noisy and converged pairs, taking auxiliary buffers such as albedo and normal as input. Reconstructs detail that hand-tuned filters smooth away, and can hallucinate detail that was never sampled.

• supersedescorrects · extends
• classifiesspecializes · part-of
• substitutes forapproximates · alternative-to
• depends onrequires · validates

Colour is the family; a dashed line is the second member of it.

This node

• alternative-tois a competing approach to Spatiotemporal Variance-Guided Filteringlearns the filter from data instead of hand-tuned weights
• requiresdoes not work without Backpropagationthe filter is learned from noisy and converged pairs

Referenced by

• extendsDiffusion Model adds capability to thisdenoises repeatedly, from pure noise, to synthesise

References

• Interactive Reconstruction of Monte Carlo Image Sequences using a Recurrent Denoising Autoencoder — Chaitanya et al. — 2017 · link