Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
AsyncPatch Diffusion: spatially-flexible image generation
Samuele Papa, Valentin De Bortoli, Guillaume Couairon +3
Standard diffusion models corrupt an entire sample with a single shared noise level, forcing all spatial regions to follow the same denoising trajectory. We introduce AsyncPatch Di…
cs.CV2024
StructuReiser: A Structure-preserving Video Stylization Method
Radim Spetlik, David Futschik, Daniel Sykora
We introduce StructuReiser, a novel video-to-video translation method that transforms input videos into stylized sequences using a set of user-provided keyframes. Unlike existing a…
cs.CV2023
Controllable Light Diffusion for Portraits
David Futschik, Kelvin Ritland, James Vecore +5
We introduce light diffusion, a novel method to improve lighting in portraits, softening harsh shadows and specular highlights while preserving overall scene illumination. Inspired…