Search papers, labs, and topics across Lattice.
The paper introduces LaS-Comp, a zero-shot, category-agnostic 3D shape completion method that leverages geometric priors from 3D foundation models. LaS-Comp employs a two-stage process: an explicit replacement stage to preserve observed geometry and an implicit refinement stage to ensure seamless boundaries. The method is evaluated on a newly introduced Omni-Comp benchmark, demonstrating superior performance compared to existing state-of-the-art approaches.
Unlock zero-shot 3D shape completion across diverse partial observations by exploiting geometric priors from 3D foundation models, without any training.
This paper introduces LaS-Comp, a zero-shot and category-agnostic approach that leverages the rich geometric priors of 3D foundation models to enable 3D shape completion across diverse types of partial observations. Our contributions are threefold: First, \ourname{} harnesses these powerful generative priors for completion through a complementary two-stage design: (i) an explicit replacement stage that preserves the partial observation geometry to ensure faithful completion; and (ii) an implicit refinement stage ensures seamless boundaries between the observed and synthesized regions. Second, our framework is training-free and compatible with different 3D foundation models. Third, we introduce Omni-Comp, a comprehensive benchmark combining real-world and synthetic data with diverse and challenging partial patterns, enabling a more thorough and realistic evaluation. Both quantitative and qualitative experiments demonstrate that our approach outperforms previous state-of-the-art approaches. Our code and data will be available at \href{https://github.com/DavidYan2001/LaS-Comp}{LaS-Comp}.
