UniWorld-View tops WorldScore with controllable novel-view video and 4D scenes

量子位 · wechat · 2026-07-24

UniWorld-View tops a world-model leaderboard with occlusion-aware novel view synthesis

The article says UniWorld-View has taken the top spot on the WorldScore leaderboard. Built by 兔展智能 together with Peking University and Peng Cheng Laboratory, the model can take one image or a short video and generate a new-view video with explicit camera control — push, pull, pan, tilt, or even a 360° orbit around the scene.

What the model does

Why large-baseline novel view synthesis is hard

The piece explains that conventional NeRF / 3DGS style reconstruction needs dense viewpoints, while diffusion-only methods often treat camera pose as a weak condition and lose control on large viewpoint changes.

The key technical ideas

Extending to 4D reconstruction

The article says the system can generate multiple views, then feed them into dynamic 3DGS for 4D reconstruction. It decouples time and camera motion by:

The broader takeaway is that the team is pushing toward a single pipeline for controllable view synthesis, open-world video generation, and 4D scene reconstruction.

Original post →

More from Multimodal

Multimodal channel →