# Learned Suppression for 3D Keypoint Detection with a Graph-Transformer Backbone

arXiv: https://arxiv.org/abs/2605.15088 · HTML: https://mlsanity.com/paper/2605.15088/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 29 of 29)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [Learning non-maximum suppression](https://mlsanity.com/paper/1705.02950/) (2017)
- [Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding](https://mlsanity.com/paper/2106.02795/) (2021)
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2112.04903/) (2021)
- [KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations](https://mlsanity.com/paper/2002.12687/) (2020)
- [PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds](https://mlsanity.com/paper/2103.02766/) (2021)
- [Skeleton Merger: an Unsupervised Aligned Keypoint Detector](https://mlsanity.com/paper/2103.10814/) (2021)
- [Building3D: An Urban-Scale Dataset and Benchmarks for Learning Roof Structures from Point Clouds](https://mlsanity.com/paper/2307.11914/) (2023)
- [3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.14084/) (2022)
- [UKPGAN: A General Self-Supervised Keypoint Detector](https://mlsanity.com/paper/2011.11974/) (2020)
- [PBWR: Parametric Building Wireframe Reconstruction from Aerial LiDAR Point Clouds](https://mlsanity.com/paper/2311.12062/) (2023)
- [BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models](https://mlsanity.com/paper/2511.06337/) (2025)

## Abstract (arXiv)

Detecting 3D keypoints is a long-standing challenge in computer vision. Most detectors end with a heuristic post-processing step that is not learned. We propose a 3D keypoint detector that improves on this step with a learned suppression module, paired with a Point Transformer backbone that we extend with a directional graph neural network. The module is a graph network over candidates that learns which to keep, which to suppress, and how to relocate the remaining ones. Paired with three backbones, it improves over DBSCAN and greedy non-maximum suppression, and because it operates on candidate features rather than raw geometry, the same formulation applies to both structural and semantic keypoints. Our model surpasses the per-category trained KeypointDETR on 12 of 16 KeypointNet categories, attains the best Corner F1 on the Building3D Entry-Level benchmark, and remains competitive with BWFormer on the larger Tallinn split. GitHub implementation: https://github.com/cansdev/learned-suppression-3d.