Toward Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups

arXiv:2601.02759 · cs.CV, cs.RO · Submitted 2026-01-06 · Read on arXiv

cs.CV, cs.RO

Submitted: 2026-01-06

Updated: 2026-10-11

Comments: 23 pages, 21 figures, TPAMI 2026. Extended version of our ICCV 2025 highlight paper [arXiv:2503.07940]. arXiv admin note: substantial text overlap with arXiv:2503.07940

Journal ref: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 48, no. 11, pp. 15234-15251, Nov. 2026

DOI: 10.1109/TPAMI.2026.3722524

Code: https://github.com/MIT-SPARK/BUFFER-X

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 2× in this paper · explained in 13 episodes
• Zero-Shot Generalization — 2× in this paper · explained in 5 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Transferability — 1× in this paper · explained in 5 episodes

Sources

• ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models
• RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning
• BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes
• Learning to Register Unbalanced Point Pairs
• Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
• A comprehensive survey on point cloud registration
• Derivation of the Euler-Rodrigues formula for three-dimensional rotations from the general formula for four-dimensional rotations
• A General and Adaptive Robust Loss Function
• ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants
• Adam: A Method for Stochastic Optimization
• Multi-Mapcher: Loop Closure Detection-Free Heterogeneous LiDAR Multi-Session SLAM Leveraging Outlier-Robust Registration for Autonomous Vehicles

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models