GUSH3R: Reconstructing Dynamic Humans & Static Scenes from Monocular Video
zhenjun_zhao · x · 2026-07-07
GUSH3R proposes a new method expressing both dynamic humans and static scenes as 3D Gaussians, enabling full-scene 3D reconstruction from a single monocular video. Combining Human3R and the SMPL-X parametric human model, it achieves collaborative 3D modeling of humans and scenes under single-camera video input. This work was published at ICML2026.
Related event: GUSH3R Enables Dynamic 3D Reconstruction from Monocular Video(2 posts)→
More from Research
- LTX 2.3 LoRA demo changes a video’s camera angle — CQDSN · 2026-07-21
- OpenForecaster uses daily news to improve language-model forecasting — Cohere_Labs · 2026-07-21
- SenseTime unveils U1 Pro and open-sources a 50M-sample vision dataset at WAIC 2026 — 机器之心 · 2026-07-21
- Baseten study finds new facts in LLM weights are fragile unless trained from many restatements — alex_verem · 2026-07-21
- Kimi K3 and Fable 5 now look much closer than the old open-vs-closed gap — FinanceYF5 · 2026-07-21
- uv-scripts/ocr returns to the top of Hugging Face datasets with a JSON model picker — vanstriendaniel · 2026-07-21