# UGG: Unified Generative Geometry Model

DevFeed: [UGG: Unified Generative Geometry Model](<https://devfeed.tech/articles/ugg-unified-generative-geometry-model-128839.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14440>)

Author: Amani Kiruga, Zhiyi Li, Ruojin Cai, Hansen Lillemark, Xiaoshan Wu, Ayush Tewari, Yilun Du

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>)

Tags: [camera](<https://devfeed.tech/tags/camera.md>), [completion](<https://devfeed.tech/tags/completion.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-models](<https://devfeed.tech/tags/generative-models.md>), [inference](<https://devfeed.tech/tags/inference.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [noise](<https://devfeed.tech/tags/noise.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [rgb](<https://devfeed.tech/tags/rgb.md>), [search](<https://devfeed.tech/tags/search.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>), [time](<https://devfeed.tech/tags/time.md>), [video](<https://devfeed.tech/tags/video.md>), [video-generation](<https://devfeed.tech/tags/video-generation.md>)

## AI overview

UGG uses one generative model to represent RGB video alongside geometry such as depth and camera pose. It assigns different noise levels across modalities and time, treating visual generation and geometric prediction as conditional completion. This lets it train on datasets with different combinations of visual and geometric annotations. At inference, it can search among multiple scene hypotheses and use geometric evidence from observed RGB frames to improve predictions without ground-truth geometry. The abstract reports results over non-unified baselines for camera-controlled video generation, depth estimation, and camera pose prediction, including sparse-observation settings; it provides no quantitative results here.

## Source excerpt

arXiv:2611.14440v1 Announce Type: cross Abstract: Understanding 4D scenes is a core challenge in visual intelligence, requiring models to jointly capture scene geometry, appearance, and dynamics from partial observations. However, existing approaches are subdivided into feedforward models for direct geometric prediction, and generative models for visual synthesis. We introduce UGG, a unified framework for 4D scene understanding that jointly models RGB video and geometric representations such as depth and camera pose. 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 flexible formulation enables the model to learn from diverse, heterogeneous datasets with different subsets of geometric and visual annotations. Furthermore, our generative formulation enables inference-time search over multiple plausible scene hypotheses, using geometric evidence extracted from observed RGB frames to improve geometric prediction without ground truth geometry. We demonstrate UGG's effectiveness over non-unified baselines across camera-controlled video generation, depth estimation, and camera pose prediction, including in challenging sparse observation settings. Code and visualizations are available at https://ugg-model.github.io/