Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
PhysReflect: Geometry and Perception Guided Diffusion for Physically-Plausible Mirror Reflections
Shuheng Ge, Hongwei Ren, Li Zhang +1
Diffusion models generate high-quality images, yet often violate the physical laws governing mirror reflections. Reflections often suffer from geometric aberrations, including posi…
cs.CV2024
OpFlowTalker: Realistic and Natural Talking Face Generation via Optical Flow Guidance
Shuheng Ge, Haoyu Xing, Li Zhang +1
Creating realistic, natural, and lip-readable talking face videos remains a formidable challenge. Previous research primarily concentrated on generating and aligning single-frame i…