Papers › Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition

Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition

8 Apr 2022arXiv:2204.03957archive 2025-07-28

Axel Berg, Magnus Oskarsson, Mark O'Connor

While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes inefficient as the set of input points grows larger. Furthermore, we find that the attention mechanism struggles to find useful connections between individual points on a global scale. In order to alleviate these problems, we propose a two-stage Point Transformer-in-Transformer (Point-TnT) approach which combines local and global attention mechanisms, enabling both individual points and patches of points to attend to each other effectively. Experiments on shape classification show that such an approach provides more useful features for downstream tasks than the baseline Transformer, while also being more computationally efficient. In addition, we also extend our method to feature matching for scene reconstruction, showing that it can be used in conjunction with existing scene reconstruction pipelines.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

axeber01/point-tnt officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline (arXiv:2106.05304; that paper's own run record: 4 ran (of which 3 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) · 8 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

3D Feature Matching3D Point Cloud Classification3D Shape RecognitionPoint Cloud Registration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40 Point-TnT Number of params 3.9M #86 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 Point-TnT Overall Accuracy 92.6 #86 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN Point-TnT FLOPs 1.19G #63 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN Point-TnT Mean Accuracy 81.0 #63 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN Point-TnT Number of params 3.9M #63 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN Point-TnT Overall Accuracy 83.5 #63 of 77 Archive leaderboard report
Point Cloud Registration 3DMatch Benchmark DIP + Point-TnT Feature Matching Recall 96.8 #6 of 15 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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