# Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation

arXiv: https://arxiv.org/abs/2201.05972 · HTML: https://mlsanity.com/paper/2201.05972/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 16 Jan 2022.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [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)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [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)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [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)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [3D Object Detection with Pointformer](https://mlsanity.com/paper/2012.11409/) (2020)
- [RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2103.12978/) (2021)
- [SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation](https://mlsanity.com/paper/2004.01803/) (2020)
- [(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2102.04530/) (2021)

## Built on by (most cited first, 22 of 22)

- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase](https://mlsanity.com/paper/2309.05573/) (2023)
- [SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion](https://mlsanity.com/paper/2306.15349/) (2023)
- [3D Vision with Transformers: A Survey](https://mlsanity.com/paper/2208.04309/) (2022)
- [PanSt3R: Multi-view Consistent Panoptic Segmentation](https://mlsanity.com/paper/2506.21348/) (2025)
- [4D Panoptic Segmentation as Invariant and Equivariant Field Prediction](https://mlsanity.com/paper/2303.15651/) (2023)
- [LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment](https://mlsanity.com/paper/2308.01686/) (2023)
- [Position-Guided Point Cloud Panoptic Segmentation Transformer](https://mlsanity.com/paper/2303.13509/) (2023)
- [3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation](https://mlsanity.com/paper/2401.02402/) (2024)
- [TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic Segmentation](https://mlsanity.com/paper/2310.02260/) (2023)
- [MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2401.16305/) (2024)
- [OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity](https://mlsanity.com/paper/2409.19987/) (2024)
- [How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation](https://mlsanity.com/paper/2505.18956/) (2025)
- [Lidar Panoptic Segmentation and Tracking without Bells and Whistles](https://mlsanity.com/paper/2310.12464/) (2023)
- [Center Focusing Network for Real-Time LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2311.09499/) (2023)
- [UP-Fuse: Uncertainty-guided LiDAR-Camera Fusion for 3D Panoptic Segmentation](https://mlsanity.com/paper/2602.19349/) (2026)
- [SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.06869/) (2023)
- [PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation](https://mlsanity.com/paper/2306.15348/) (2023)
- [Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baseline](https://mlsanity.com/paper/2503.13203/) (2025)
- [DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries](https://mlsanity.com/paper/2408.15813/) (2024)
- [PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2604.19379/) (2026)
- [Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation](https://mlsanity.com/paper/2606.31609/) (2026)

## Abstract (arXiv)

Two major challenges of 3D LiDAR Panoptic Segmentation (PS) are that point clouds of an object are surface-aggregated and thus hard to model the long-range dependency especially for large instances, and that objects are too close to separate each other. Recent literature addresses these problems by time-consuming grouping processes such as dual-clustering, mean-shift offsets, etc., or by bird-eye-view (BEV) dense centroid representation that downplays geometry. However, the long-range geometry relationship has not been sufficiently modeled by local feature learning from the above methods. To this end, we present SCAN, a novel sparse cross-scale attention network to first align multi-scale sparse features with global voxel-encoded attention to capture the long-range relationship of instance context, which can boost the regression accuracy of the over-segmented large objects. For the surface-aggregated points, SCAN adopts a novel sparse class-agnostic representation of instance centroids, which can not only maintain the sparsity of aligned features to solve the under-segmentation on small objects, but also reduce the computation amount of the network through sparse convolution. Our method outperforms previous methods by a large margin in the SemanticKITTI dataset for the challenging 3D PS task, achieving 1st place with a real-time inference speed.