UGG: Unified Generative Geometry Model
UGG: Unified Generative Geometry Model
This paper introduces UGG, a unified framework for understanding 4D scenes that jointly captures geometry, appearance, and dynamics from partial observations. By assigning different noise levels across modalities and time, UGG formulates visual generation and geometric prediction as conditional completion within a single generative model. This approach allows the model to learn from diverse datasets with heterogeneous annotations and enables inference-time search over multiple plausible scene hypotheses using geometric evidence from observed RGB frames. The authors demonstrate UGG's effectiveness over non-unified baselines in camera-controlled video generation, depth estimation, and camera pose prediction, including in sparse observation settings. Code and visualizations are available at https://ugg-model.github.io/.
The authors present UGG, a unified generative framework for 4D scene understanding that jointly models RGB video and geometric representations like depth and camera pose within a single model, enabling inference-time search over plausible scene hypotheses without requiring ground truth geometry.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: Available Artifact link Open source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
nging sparse observation settings. Code and visualizations are available at https://ugg-model.github.io/
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org