UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding
This work addresses the problem of fragmented 3D AI capabilities for researchers and practitioners, offering a novel unified approach that is not incremental.
The paper tackles the challenge of integrating 3D tasks into a unified framework for understanding and generation, resulting in a method that demonstrates superiority in visual representation, spatial understanding, and 3D generation.
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.