2 citations · 3 across the 10 of their papers we have counts for
4 papers · 1 filter
Edge-preserving noise for diffusion models
Jente Vandersanden, Sascha Holl, Xingchang Huang +1
Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information important for high-quality generation.…
Jump Restore Light Transport
Sascha Holl, Gurprit Singh, Hans-Peter Seidel
Markov chain Monte Carlo (MCMC) algorithms are indispensable when sampling from a complex, high-dimensional distribution by a conventional method is intractable. Even though MCMC i…
Multiple Importance Sampling for Stochastic Gradient Estimation
Corentin Salaün, Xingchang Huang, Iliyan Georgiev +2
We introduce a theoretical and practical framework for efficient importance sampling of mini-batch samples for gradient estimation from single and multiple probability distribution…
Blue noise for diffusion models
Xingchang Huang, Corentin Salaün, Cristina Vasconcelos +3
Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed b…