Harvard-MIT UGG model unifies video generation, depth and camera pose in one diffusion model
burny_tech · x · 2026-11-14
UGG, from Harvard, MIT and UC San Diego researchers, unifies video generation, depth estimation and camera pose prediction—tasks usually handled separately—into a single generative diffusion model. By assigning different noise levels across modalities, it treats visual generation and geometric prediction as conditional completion, trains on heterogeneous datasets with partial annotations, and searches over multiple 3D hypotheses at inference time. It beats Geo4D on ScanNet++ camera pose estimation and outperforms specialized video gen models, especially with sparse observations. Code: ugg-model.github.io
More from Multimodal
- Encoder-free VLMs gain momentum as new study tackles scaling and architecture questions — liuziwei7 · 2026-11-14
- CapCut Web Ultra Offers a Week of Unlimited Seedream and GPT Image 2.5 Generation — JaynitMakwana · 2026-11-14
- Solv3R demo impresses: 3DGS reconstruction runs in about a minute — jonstephens85 · 2026-11-14
- Dreamina allegedly paid $82k in 'labor' for a 4-minute AI video — AIandDesign · 2026-11-14
- CapCut Adds Seedance 2.5 for 4K Video Generation in AI Lab and Video Studio — CurieuxExplorer · 2026-11-14
- BAAI's encoder-free VLM family EVE: NeurIPS spotlight, ICCV highlight, open-sourced — liuziwei7 · 2026-11-14