research
∙
05/05/2023
Iterative α-(de)Blending: a Minimalist Deterministic Diffusion Model
We derive a minimalist but powerful deterministic denoising-diffusion mo...
share
research
∙
03/22/2022
Bringing Linearly Transformed Cosines to Anisotropic GGX
Linearly Transformed Cosines (LTCs) are a family of distributions that a...
research
∙
05/27/2021
Passing Multi-Channel Material Textures to a 3-Channel Loss
Our objective is to compute a textural loss that can be used to train te...
research
∙
05/26/2021
Lessons Learned and Improvements when Building Screen-Space Samplers with Blue-Noise Error Distribution
Recent work has shown that the error of Monte-Carlo rendering is visuall...
research
∙
06/12/2020
Pitfalls of the Gram Loss for Neural Texture Synthesis in Light of Deep Feature Histograms
Neural texture synthesis and style transfer are both powered by the Gram...
research
∙
07/26/2017