Yihao Wang

Orbia: Do Generated Videos Form a Consistent 3D World?

Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision-language models to judge memory and consistency, leaving systematic 3D evaluati...

Articulation Perception from In-the-Wild Egocentric Hand–Object Interactions

Orbia: Do Generated Videos Form a Consistent 3D World?

Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision-language models to judge memory and consistency, leaving systematic 3D evaluati...

SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis

Across RealEstate10K, DL3DV, Tanks-and-Temples, and Mip-NeRF 360, SplatGuide achieves state-of-the-art pose-free novel view synthesis, and surpasses the ground-truth-pose baseline.