# LitePT: Lighter Yet Stronger Point Transformer

arXiv: https://arxiv.org/abs/2512.13689 · HTML: https://mlsanity.com/paper/2512.13689/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 82 of its 105 references that are in the map.
- First posted on arXiv 15 Dec 2025.

## Builds on (most cited first, 30 of 82)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [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)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [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)
- [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)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [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)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)

## Built on by (most cited first, 17 of 17)

- [Utonia: Toward One Encoder for All Point Clouds](https://mlsanity.com/paper/2603.03283/) (2026)
- [TORA: Topological Representation Alignment for 3D Shape Assembly](https://mlsanity.com/paper/2604.04050/) (2026)
- [Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding](https://mlsanity.com/paper/2604.19609/) (2026)
- [No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos](https://mlsanity.com/paper/2605.22190/) (2026)
- [RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings](https://mlsanity.com/paper/2605.10706/) (2026)
- [Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics](https://mlsanity.com/paper/2609.00611/) (2026)
- [PointTransformerX: Portable and Efficient 3D Point Cloud Processing without Sparse Algorithms](https://mlsanity.com/paper/2604.24169/) (2026)
- [From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments](https://mlsanity.com/paper/2605.02098/) (2026)
- [Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction](https://mlsanity.com/paper/2605.15923/) (2026)
- [Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects](https://mlsanity.com/paper/2605.28270/) (2026)
- [Vanilla ViT for Automotive Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2605.31177/) (2026)
- [An Enhanced Geometric-Spectral Feature Learning Framework for Airborne Multispectral Point Cloud Classification](https://mlsanity.com/paper/2606.09123/) (2026)
- [PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models](https://mlsanity.com/paper/2606.16569/) (2026)
- [Intrinsic and Triangulation-Agnostic Attention: A Simple and Powerful Approach for Learning on Meshes](https://mlsanity.com/paper/2607.24954/) (2026)
- [Polis: 3D Self-Supervision at City Scale](https://mlsanity.com/paper/2608.29426/) (2026)
- [GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting](https://mlsanity.com/paper/2609.09082/) (2026)
- [Toward a foundation model for forest point clouds](https://mlsanity.com/paper/2609.24787/) (2026)

## Abstract (arXiv)

Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains unclear. We analyse the role of different computational blocks in 3D point cloud networks and find an intuitive behaviour: convolution is adequate to extract low-level geometry at high-resolution in early layers, where attention is expensive without bringing any benefits; attention captures high-level semantics and context in low-resolution, deep layers more efficiently, where convolution inflates the parameter count. Guided by this design principle, we propose a new, improved 3D point cloud backbone that employs convolutions in early stages and switches to attention for deeper layers. To avoid the loss of spatial layout information when discarding redundant convolution layers, we introduce a novel, parameter-free 3D positional encoding, PointROPE. The resulting LitePT model has 3.6× fewer parameters, runs 2× faster, and uses 2× less memory than the state-of-the-art Point Transformer V3, but nonetheless matches or outperforms it on a range of tasks and datasets. Code and models are available at: https://github.com/prs-eth/LitePT.