14 citations · 20 across the 2 of their papers we have counts for
3 papers
cs.GR2023★ 14 cited
Iterative -(de)Blending: a Minimalist Deterministic Diffusion Model
Eric Heitz, Laurent Belcour, Thomas Chambon
We derive a minimalist but powerful deterministic denoising-diffusion model. While denoising diffusion has shown great success in many domains, its underlying theory remains largel…
cs.GR2021★ 6 cited
Passing Multi-Channel Material Textures to a 3-Channel Loss
Thomas Chambon, Eric Heitz, Laurent Belcour
Our objective is to compute a textural loss that can be used to train texture generators with multiple material channels typically used for physically based rendering such as albed…
cs.CV2020
A Sliced Wasserstein Loss for Neural Texture Synthesis
Eric Heitz, Kenneth Vanhoey, Thomas Chambon +1
We address the problem of computing a textural loss based on the statistics extracted from the feature activations of a convolutional neural network optimized for object recognitio…