Papers › 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions

3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions

27 Mar 2016CVPR 2017 7arXiv:1603.08182archive 2025-07-28

Andy Zeng, Shuran Song, Matthias Nießner, Matthew Fisher, Jianxiong Xiao, Thomas Funkhouser

Matching local geometric features on real-world depth images is a challenging task due to the noisy, low-resolution, and incomplete nature of 3D scan data. These difficulties limit the performance of current state-of-art methods, which are typically based on histograms over geometric properties. In this paper, we present 3DMatch, a data-driven model that learns a local volumetric patch descriptor for establishing correspondences between partial 3D data. To amass training data for our model, we propose a self-supervised feature learning method that leverages the millions of correspondence labels found in existing RGB-D reconstructions. Experiments show that our descriptor is not only able to match local geometry in new scenes for reconstruction, but also generalize to different tasks and spatial scales (e.g. instance-level object model alignment for the Amazon Picking Challenge, and mesh surface correspondence). Results show that 3DMatch consistently outperforms other state-of-the-art approaches by a significant margin. Code, data, benchmarks, and pre-trained models are available online at http://3dmatch.cs.princeton.edu

PaperPDFConference PDFCode

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

Code

andyzeng/3dmatch-toolbox officialmentioned on GitHubBSD-2-Clause report
dengzhi-ustc/a-robust-registration-loss mentioned 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

3D ReconstructionPoint Cloud Registration

Datasets

Introduced by this paper, per the archive.

3DMatch

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Reconstruction Scan2CAD 3DMatch Average Accuracy 10.29% #2 of 2 Archive leaderboard report
Point Cloud Registration 3DMatch Benchmark 3DMatch + RANSAC Feature Matching Recall 66.8 #13 of 15 Archive leaderboard report
Point Cloud Registration ETH (trained on 3DMatch) 3DMatch Feature Matching Recall 0.169 #10 of 20 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.

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