# SP2T: Sparse Proxy Attention for Dual-stream Point Transformer

arXiv: https://arxiv.org/abs/2412.11540 · HTML: https://mlsanity.com/paper/2412.11540/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 70 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [How Do Vision Transformers Work?](https://mlsanity.com/paper/2202.06709/) (2022)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)

## Built on by (most cited first, 3 of 3)

- [EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence](https://mlsanity.com/paper/2512.15160/) (2025)
- [AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction](https://mlsanity.com/paper/2512.19150/) (2025)
- [Online Navigation Refinement: Achieving Lane-Level Guidance by Associating Standard-Definition and Online Perception Maps](https://mlsanity.com/paper/2507.07487/) (2025)

## Abstract (arXiv)

Point transformers have demonstrated remarkable progress in 3D understanding through expanded receptive fields (RF), but further expanding the RF leads to dilution in group attention and decreases detailed feature extraction capability. Proxy, which serves as abstract representations for simplifying feature maps, enables global RF. However, existing proxy-based approaches face critical limitations: Global proxies incur quadratic complexity for large-scale point clouds and suffer positional ambiguity, while local proxy alternatives struggle with 1) Unreliable sampling from the geometrically diverse point cloud, 2) Inefficient proxy interaction computation, and 3) Imbalanced local-global information fusion; To address these challenges, we propose Sparse Proxy Point Transformer (SP2T) -- a local proxy-based dual-stream point transformer with three key innovations: First, for reliable sampling, spatial-wise proxy sampling with vertex-based associations enables robust sampling on geometrically diverse point clouds. Second, for efficient proxy interaction, sparse proxy attention with a table-based relative bias effectively achieves the interaction with efficient map-reduce computation. Third, for local-global information fusion, our dual-stream architecture maintains local-global balance through parallel branches. Comprehensive experiments reveal that SP2T sets state-of-the-art results with acceptable latency on indoor and outdoor 3D comprehension benchmarks, demonstrating marked improvement (+3.8% mIoU vs. SPoTr@S3DIS, +22.9% mIoU vs. PointASNL@Sem.KITTI) compared to other proxy-based point cloud methods.