3 papers
math.PR2024
Concatenation of Markov processes
Sascha Holl
We investigate the concatenation of Markov processes. Our primary concern is to utilize processes constructed in this manner for Monte Carlo integration. To enable this using conve…
cs.CV2024
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.…
cs.GR2024
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…