Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding
This addresses the challenge of enhancing 3D point cloud analysis without additional training, which is significant for applications in robotics and autonomous systems, though it is incremental as it builds on existing 2D Vision-Language Model methods.
The paper tackles the problem of zero-shot 3D point cloud understanding by introducing a training-free aggregation technique that leverages geometric structure to improve Vision-Language Model transfers, achieving new state-of-the-art results across classification, part segmentation, and semantic segmentation benchmarks.
Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs). Existing strategies directly map Vision-Language Models from 2D pixels of rendered or captured views to 3D points, overlooking the inherent and expressible point cloud geometric structure. Geometrically similar or close regions can be exploited for bolstering point cloud understanding as they are likely to share semantic information. To this end, we introduce the first training-free aggregation technique that leverages the point cloud's 3D geometric structure to improve the quality of the transferred Vision-Language Models. Our approach operates iteratively, performing local-to-global aggregation based on geometric and semantic point-level reasoning. We benchmark our approach on three downstream tasks, including classification, part segmentation, and semantic segmentation, with a variety of datasets representing both synthetic/real-world, and indoor/outdoor scenarios. Our approach achieves new state-of-the-art results in all benchmarks. Our approach operates iteratively, performing local-to-global aggregation based on geometric and semantic point-level reasoning. Code and dataset are available at https://luigiriz.github.io/geoze-website/