Papers › You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

1 Sep 2021arXiv:2109.00182archive 2025-07-28

Haiping Wang, YuAn Liu, Zhen Dong, Wenping Wang

In this paper, we propose a novel local descriptor-based framework, called You Only Hypothesize Once (YOHO), for the registration of two unaligned point clouds. In contrast to most existing local descriptors which rely on a fragile local reference frame to gain rotation invariance, the proposed descriptor achieves the rotation invariance by recent technologies of group equivariant feature learning, which brings more robustness to point density and noise. Meanwhile, the descriptor in YOHO also has a rotation equivariant part, which enables us to estimate the registration from just one correspondence hypothesis. Such property reduces the searching space for feasible transformations, thus greatly improves both the accuracy and the efficiency of YOHO. Extensive experiments show that YOHO achieves superior performances with much fewer needed RANSAC iterations on four widely-used datasets, the 3DMatch/3DLoMatch datasets, the ETH dataset and the WHU-TLS dataset. More details are shown in our project page: https://hpwang-whu.github.io/YOHO/.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

HpWang-whu/YOHO officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Point Cloud Registration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Cloud Registration ETH (trained on 3DMatch) YOHO-C Recall (30cm, 5 degrees) 84.85 #15 of 20 Archive leaderboard report
Point Cloud Registration ETH (trained on 3DMatch) YOHO-O Recall (30cm, 5 degrees) 79.94 #16 of 20 Archive leaderboard report
Point Cloud Registration FPv1 FCGF + YOHO-C RRE (degrees) 3.653 #6 of 8 Archive leaderboard report
Point Cloud Registration FPv1 FCGF + YOHO-C RTE (cm) 1.668 #6 of 8 Archive leaderboard report
Point Cloud Registration FPv1 FCGF + YOHO-C Recall (3cm, 10 degrees) 29.18 #6 of 8 Archive leaderboard report
Point Cloud Registration FPv1 FCGF + YOHO-O RRE (degrees) 4.489 #7 of 8 Archive leaderboard report
Point Cloud Registration FPv1 FCGF + YOHO-O RTE (cm) 1.852 #7 of 8 Archive leaderboard report
Point Cloud Registration FPv1 FCGF + YOHO-O Recall (3cm, 10 degrees) 18.91 #7 of 8 Archive leaderboard report
Point Cloud Registration KITTI (trained on 3DMatch) YOHO-C Success Rate 82.16 #8 of 14 Archive leaderboard report
Point Cloud Registration KITTI (trained on 3DMatch) YOHO-O Success Rate 81.44 #10 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

YOHO

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections