Score: 0

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding

Published: August 16, 2025 | arXiv ID: 2508.11952v1

By: Yueming Xu , Jiahui Zhang , Ze Huang and more

Potential Business Impact:

Creates 3D worlds from pictures and words.

Despite the impressive progress on understanding and generating images shown by the recent unified architectures, the integration of 3D tasks remains challenging and largely unexplored. In this paper, we introduce UniUGG, the first unified understanding and generation framework for 3D modalities. Our unified framework employs an LLM to comprehend and decode sentences and 3D representations. At its core, we propose a spatial decoder leveraging a latent diffusion model to generate high-quality 3D representations. This allows for the generation and imagination of 3D scenes based on a reference image and an arbitrary view transformation, while remaining supports for spatial visual question answering (VQA) tasks. Additionally, we propose a geometric-semantic learning strategy to pretrain the vision encoder. This design jointly captures the input's semantic and geometric cues, enhancing both spatial understanding and generation. Extensive experimental results demonstrate the superiority of our method in visual representation, spatial understanding, and 3D generation. The source code will be released upon paper acceptance.

Country of Origin
🇨🇳 China

Page Count
15 pages

Category
Computer Science:
CV and Pattern Recognition