# 3D Object Detection with Pointformer

arXiv: https://arxiv.org/abs/2012.11409 · HTML: https://mlsanity.com/paper/2012.11409/

## Key facts

- Cited by 194 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 30 of 194)

- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [Voxel Transformer for 3D Object Detection](https://mlsanity.com/paper/2109.02497/) (2021)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [Omnivore: A Single Model for Many Visual Modalities](https://mlsanity.com/paper/2201.08377/) (2022)
- [Embracing Single Stride 3D Object Detector with Sparse Transformer](https://mlsanity.com/paper/2112.06375/) (2021)
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets](https://mlsanity.com/paper/2301.06051/) (2023)
- [A Survey of Visual Transformers](https://mlsanity.com/paper/2111.06091/) (2021)
- [TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers](https://mlsanity.com/paper/2111.14600/) (2021)
- [Improving 3D Object Detection with Channel-wise Transformer](https://mlsanity.com/paper/2108.10723/) (2021)
- [Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds](https://mlsanity.com/paper/2203.10314/) (2022)
- [SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2210.07372/) (2022)
- [InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding](https://mlsanity.com/paper/2203.07997/) (2022)
- [AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds](https://mlsanity.com/paper/2112.09205/) (2021)
- [Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers](https://mlsanity.com/paper/2304.10716/) (2023)
- [M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers](https://mlsanity.com/paper/2104.11896/) (2021)
- [On the Integration of Self-Attention and Convolution](https://mlsanity.com/paper/2111.14556/) (2021)
- [FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer](https://mlsanity.com/paper/2301.08739/) (2023)
- [Bird's-Eye-View Scene Graph for Vision-Language Navigation](https://mlsanity.com/paper/2308.04758/) (2023)
- [Point Density-Aware Voxels for LiDAR 3D Object Detection](https://mlsanity.com/paper/2203.05662/) (2022)
- [E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning](https://mlsanity.com/paper/2307.13770/) (2023)
- [MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2303.08600/) (2023)
- [Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2203.04845/) (2022)
- [CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer](https://mlsanity.com/paper/2209.06535/) (2022)

## Abstract (arXiv)

Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively. Specifically, a Local Transformer module is employed to model interactions among points in a local region, which learns context-dependent region features at an object level. A Global Transformer is designed to learn context-aware representations at the scene level. To further capture the dependencies among multi-scale representations, we propose Local-Global Transformer to integrate local features with global features from higher resolution. In addition, we introduce an efficient coordinate refinement module to shift down-sampled points closer to object centroids, which improves object proposal generation. We use Pointformer as the backbone for state-of-the-art object detection models and demonstrate significant improvements over original models on both indoor and outdoor datasets.