# Point Transformer V3: Simpler, Faster, Stronger

arXiv: https://arxiv.org/abs/2312.10035 · HTML: https://mlsanity.com/paper/2312.10035/

## Key facts

- Cited by 589 papers in the map (data through 14 Oct 2026).
- Builds on 87 of its 106 references that are in the map.
- First posted on arXiv 15 Dec 2023.

## Builds on (most cited first, 30 of 87)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [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)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [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)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)

## Built on by (most cited first, 30 of 589)

- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [SAMPart3D: Segment Any Part in 3D Objects](https://mlsanity.com/paper/2411.07184/) (2024)
- [PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation](https://mlsanity.com/paper/2601.03782/) (2026)
- [BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models](https://mlsanity.com/paper/2506.07961/) (2025)
- [Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy](https://mlsanity.com/paper/2403.06467/) (2024)
- [Large Spatial Model: End-to-end Unposed Images to Semantic 3D](https://mlsanity.com/paper/2410.18956/) (2024)
- [Point Cloud Mamba: Point Cloud Learning via State Space Model](https://mlsanity.com/paper/2403.00762/) (2024)
- [Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection](https://mlsanity.com/paper/2406.10700/) (2024)
- [SpatialLM: Training Large Language Models for Structured Indoor Modeling](https://mlsanity.com/paper/2506.07491/) (2025)
- [Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model](https://mlsanity.com/paper/2404.14966/) (2024)
- [SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining](https://mlsanity.com/paper/2503.18052/) (2025)
- [Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration](https://mlsanity.com/paper/2502.16652/) (2025)
- [TEXGen: a Generative Diffusion Model for Mesh Textures](https://mlsanity.com/paper/2411.14740/) (2024)
- [Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations](https://mlsanity.com/paper/2510.23607/) (2025)
- [OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation](https://mlsanity.com/paper/2403.14418/) (2024)
- [Generative Gaussian Splatting for Unbounded 3D City Generation](https://mlsanity.com/paper/2406.06526/) (2024)
- [Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning](https://mlsanity.com/paper/2410.08114/) (2024)
- [P3-SAM: Native 3D Part Segmentation](https://mlsanity.com/paper/2509.06784/) (2025)
- [Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy](https://mlsanity.com/paper/2410.01345/) (2024)
- [Training-Free Efficient Video Generation via Dynamic Token Carving](https://mlsanity.com/paper/2505.16864/) (2025)
- [Find Any Part in 3D](https://mlsanity.com/paper/2411.13550/) (2024)
- [GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training](https://mlsanity.com/paper/2507.13097/) (2025)
- [DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation](https://mlsanity.com/paper/2503.18944/) (2025)
- [PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection](https://mlsanity.com/paper/2412.12617/) (2024)
- [OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation](https://mlsanity.com/paper/2504.09975/) (2025)
- [MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments](https://mlsanity.com/paper/2503.02579/) (2025)
- [Spatial Understanding from Videos: Structured Prompts Meet Simulation Data](https://mlsanity.com/paper/2506.03642/) (2025)

## Abstract (arXiv)

This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing, leveraging the power of scale. Drawing inspiration from recent advances in 3D large-scale representation learning, we recognize that model performance is more influenced by scale than by intricate design. Therefore, we present Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the overall performance after scaling, such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns. This principle enables significant scaling, expanding the receptive field from 16 to 1024 points while remaining efficient (a 3x increase in processing speed and a 10x improvement in memory efficiency compared with its predecessor, PTv2). PTv3 attains state-of-the-art results on over 20 downstream tasks that span both indoor and outdoor scenarios. Further enhanced with multi-dataset joint training, PTv3 pushes these results to a higher level.