4DAnyone: Create Anyone in 4D from a Casual Monocular Video

Ant Research

Research official 3 src. ~1 min

Reconstructs animatable 4D humans from an uncalibrated monocular video by generating reconstruction-grade, multi-view-consistent videos via a camera-controlled video diffusion model and lifting them to 4D Gaussian Splatting; introduces Reference Context Packing and Target Context Routing plus the MVGameHuman dataset.

Why it matters

HF Daily Paper with 317 upvotes; accepted at SIGGRAPH Asia, first practical casual-video → 4DGS pipeline

Importance: 3/5

HF Daily Paper with 317 upvotes

4d-reconstruction video-diffusion gaussian-splatting multimodal computer-vision long-video

Sources

official 4DAnyone: Create Anyone in 4D from a Casual Monocular Video

official HF Daily Paper page for 4DAnyone

official AntResearch/4DAnyone (Apache-2.0 code + model)