Neural Denoising for Spectral Monte Carlo Rendering - Université de Reims Champagne-Ardenne Access content directly
Conference Poster Year : 2022

Neural Denoising for Spectral Monte Carlo Rendering

Abstract

Spectral Monte Carlo (MC) rendering is still to be largely adopted partially due to the specific noise, called color noise, induced by wavelength-dependent phenomenons. Motivated by the recent advances in Monte Carlo noise reduction using Deep Learning, we propose to apply the same approach to color noise. Our implementation and training managed to reconstruct a noise-free output while conserving high-frequency details despite a loss of contrast. To address this issue, we designed a three-step pipeline using the contribution of a secondary denoiser to obtain high-quality results.
Fichier principal
Vignette du fichier
poster EG2022_LUCE.pdf (2.24 Mo) Télécharger le fichier
EG22.pdf (13.56 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04042962 , version 1 (23-03-2023)

Identifiers

Cite

Robin Rouphael, Mathieu Noizet, Stéphanie Prévost, Hervé Deleau, Luiz-Angelo Steffenel, et al.. Neural Denoising for Spectral Monte Carlo Rendering. Eurographics 2022, Apr 2022, Reims, France. , Eurographics 2022 - Posters, 2022, ⟨10.2312/egp.20221011⟩. ⟨hal-04042962⟩

Collections

URCA ANR LICIIS
60 View
48 Download

Altmetric

Share

Gmail Facebook X LinkedIn More