BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes
This addresses the need for robust point cloud registration in diverse scenes without manual adjustments, though it is incremental as it builds on existing methods to improve generalization.
The paper tackles the problem of point cloud registration requiring retraining or manual tuning for new environments by proposing BUFFER-X, a zero-shot pipeline that adaptively determines parameters, uses farthest point sampling, and applies patch-wise scale normalization, achieving substantial generalization across 11 diverse datasets without prior information.
Recent advances in deep learning-based point cloud registration have improved generalization, yet most methods still require retraining or manual parameter tuning for each new environment. In this paper, we identify three key factors limiting generalization: (a) reliance on environment-specific voxel size and search radius, (b) poor out-of-domain robustness of learning-based keypoint detectors, and (c) raw coordinate usage, which exacerbates scale discrepancies. To address these issues, we present a zero-shot registration pipeline called BUFFER-X by (a) adaptively determining voxel size/search radii, (b) using farthest point sampling to bypass learned detectors, and (c) leveraging patch-wise scale normalization for consistent coordinate bounds. In particular, we present a multi-scale patch-based descriptor generation and a hierarchical inlier search across scales to improve robustness in diverse scenes. We also propose a novel generalizability benchmark using 11 datasets that cover various indoor/outdoor scenarios and sensor modalities, demonstrating that BUFFER-X achieves substantial generalization without prior information or manual parameter tuning for the test datasets. Our code is available at https://github.com/MIT-SPARK/BUFFER-X.