PREDATOR: Registration of 3D Point Clouds with Low Overlap

CVPR 2021  ·  Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, Konrad Schindler ·

We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region. Different from previous work, our model is specifically designed to handle (also) point-cloud pairs with low overlap. Its key novelty is an overlap-attention block for early information exchange between the latent encodings of the two point clouds. In this way the subsequent decoding of the latent representations into per-point features is conditioned on the respective other point cloud, and thus can predict which points are not only salient, but also lie in the overlap region between the two point clouds. The ability to focus on points that are relevant for matching greatly improves performance: PREDATOR raises the rate of successful registrations by more than 20% in the low-overlap scenario, and also sets a new state of the art for the 3DMatch benchmark with 89% registration recall.

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Point Cloud Registration 3DLoMatch (10-30% overlap) Predator-1k Recall ( correspondence RMSE below 0.2) 62.5 # 4
Compare
Point Cloud Registration 3DLoMatch (10-30% overlap) Predator-NR Recall ( correspondence RMSE below 0.2) 24 # 11
Compare
Point Cloud Registration 3DLoMatch (10-30% overlap) Predator-5k Recall ( correspondence RMSE below 0.2) 59.8 # 5
Compare
Point Cloud Registration 3DMatch (at least 30% overlapped - sample 5k interest points) Predator-5k Recall ( correspondence RMSE below 0.2) 89 # 4
Compare
Point Cloud Registration 3DMatch (at least 30% overlapped - sample 5k interest points) Predator-1k Recall ( correspondence RMSE below 0.2) 90.5 # 3
Compare
Point Cloud Registration 3DMatch (at least 30% overlapped - sample 5k interest points) Predator-NR Recall ( correspondence RMSE below 0.2) 62.7 # 10
Compare
Point Cloud Registration KITTI (trained on 3DMatch) Predator Success Rate 41.20 # 12
Compare

Methods
Add Remove

Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy