pith. sign in

arxiv: 2112.14381 · v2 · pith:BR5LTCXVnew · submitted 2021-12-29 · 💻 cs.CV

COTReg:Coupled Optimal Transport based Point Cloud Registration

Guofeng Mei , Xiaoshui Huang , Litao Yu , Jian Zhang , Mohammed Bennamoun This is my paper
classification 💻 cs.CV
keywords pointcorrespondencescloudregistrationcotregcoupleddistance-basedlike
0
0 comments X
read the original abstract

Generating a set of high-quality correspondences or matches is one of the most critical steps in point cloud registration. This paper proposes a learning framework COTReg by jointly considering the pointwise and structural matchings to predict correspondences of 3D point cloud registration. Specifically, we transform the two matchings into a Wasserstein distance-based and a Gromov-Wasserstein distance-based optimizations, respectively. Thus the task of establishing the correspondences can be naturally reshaped to a coupled optimal transport problem. Furthermore, we design a network to predict the confidence score of being an inlier for each point of the point clouds, which provides the overlap region information to generate correspondences. Our correspondence prediction pipeline can be easily integrated into either learning-based features like FCGF or traditional descriptors like FPFH. We conducted comprehensive experiments on 3DMatch, KITTI, 3DCSR, and ModelNet40 benchmarks, showing the state-of-art performance of the proposed method.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning

    cs.GR 2026-05 unverdicted novelty 7.0

    QuadLink generates anisotropic quad-dominant meshes from point clouds via anchor prediction, centroid-conditioned linking, and quad-first assembly, supporting hybrid n-gon topology.

  2. QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning

    cs.GR 2026-05 unverdicted novelty 6.0

    QuadLink generates anisotropic quad-dominant meshes from point clouds via a hybrid centroid-conditioned vertex linking model and a Tri-to-Quad data conversion operator.

  3. Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration

    cs.CV 2023-12 unverdicted novelty 6.0

    Diff-PCR uses a diffusion model to learn denoising directions for refining doubly stochastic correspondence matrices, improving point cloud registration over one-shot normalization methods.

  4. QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning

    cs.GR 2026-05 unverdicted novelty 4.0

    QuadLink generates anisotropic quad-dominant meshes from point clouds via autoregressive anchor prediction and centroid-conditioned linking, with a Tri-to-Quad data converter and quad-first assembly.