Datasets › 3DMatch

3DMatch

Introduced by Andy Zeng et al. in 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions archive 2025-07-28

The 3DMATCH benchmark evaluates how well descriptors (both 2D and 3D) can establish correspondences between RGB-D frames of different views. The dataset contains 2D RGB-D patches and 3D patches (local TDF voxel grid volumes) of wide-baselined correspondences.

The pixel size of each 2D patch is determined by the projection of the 0.3m3 local 3D patch around the interest point onto the image plane.

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

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Point Cloud Registration 3DMatch Benchmark IMFNet Feature Matching Recall 98.6 IMFNet: Interpretable Multimodal Fusion for Point Cloud... XiaoshuiHuang/IMFNet 15 Compare
3D Feature Matching 3DMatch Benchmark FCGF Average Recall 0.9578 Fully Convolutional Geometric Features chrischoy/FCGF 1 Compare
Low-Light Image Enhancement 3DMatch Benchmark nnh mAP (@0.1, Through-wall) 224 Attention Guided Low-light Image Enhancement with a... Lvfeifan/MBLLEN +2 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 15 · with a code link: 15 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (4 of 15 with a benchmark row: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 15 of 15 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 175. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition 1 1 8 Apr 2022 not harvested
IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration 1 1 18 Nov 2021 not harvested
Learning general and distinctive 3D local deep descriptors for point cloud registration 1 1 21 May 2021 not harvested
3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning 1 1 26 Mar 2021 not harvested
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration 1 1 24 Nov 2020 official: harvested, nothing ran · 0 ran · 1 unverified
Distinctive 3D local deep descriptors 2 1 1 Sep 2020 not harvested
End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds 1 1 12 Mar 2020 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features 2 2 6 Mar 2020 official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Fully Convolutional Geometric Features 1 2 27 Oct 2019 not harvested
Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset 3 1 2 Aug 2019 not harvested
The Perfect Match: 3D Point Cloud Matching with Smoothed Densities 2 1 16 Nov 2018 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors 2 1 30 Aug 2018 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (2 pointer-only for licence)
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching 1 1 7 Feb 2018 not harvested
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions 2 1 27 Mar 2016 not harvested
Fast Point Feature Histograms (FPFH) for 3D Registration 1 1 12 May 2009 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

Various

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • 3DMatch Benchmark
  • 3DMatch

2 variant names, as the archive lists them.

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