RealMe builds 2K 4D-consistent volumetric video from sparse captures
A high-resolution video diffusion model refines limited multi-view captures and beats prior methods on DNA-Rendering and RealVV.
2 stories, newest first · one card per story
A high-resolution video diffusion model refines limited multi-view captures and beats prior methods on DNA-Rendering and RealVV.
Seed Injection and Temporal Biased Relocation keep a fixed Gaussian budget while recovering small, fast-moving objects.
Today 1.5K readers · 2.4K views · 768 reads · all time 189K views