# LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment

arXiv: https://arxiv.org/abs/2103.02263 · HTML: https://mlsanity.com/paper/2103.02263/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 3 Mar 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [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)
- [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)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [Deep Feature Flow for Video Recognition](https://mlsanity.com/paper/1611.07715/) (2016)
- [SEGCloud: Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1710.07563/) (2017)
- [Tangent Convolutions for Dense Prediction in 3D](https://mlsanity.com/paper/1807.02443/) (2018)
- [SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation](https://mlsanity.com/paper/2004.01803/) (2020)
- [Deep Parametric Continuous Convolutional Neural Networks](https://mlsanity.com/paper/2101.06742/) (2021)
- [Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark](https://mlsanity.com/paper/1704.03847/) (2017)
- [SPLATNet: Sparse Lattice Networks for Point Cloud Processing](https://mlsanity.com/paper/1802.08275/) (2018)
- [Delving Deeper into Convolutional Networks for Learning Video Representations](https://mlsanity.com/paper/1511.06432/) (2015)
- [LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving](https://mlsanity.com/paper/1903.08701/) (2019)
- [Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video](https://mlsanity.com/paper/1807.06667/) (2018)
- [Semantic Video CNNs through Representation Warping](https://mlsanity.com/paper/1708.03088/) (2017)
- [Paris-Lille-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification](https://mlsanity.com/paper/1712.00032/) (2017)
- [LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention](https://mlsanity.com/paper/2004.01389/) (2020)
- [3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation](https://mlsanity.com/paper/2002.10893/) (2020)

## Built on by (most cited first, 26 of 26)

- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://mlsanity.com/paper/2210.08064/) (2022)
- [Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions](https://mlsanity.com/paper/2206.04129/) (2022)
- [4D Contrastive Superflows are Dense 3D Representation Learners](https://mlsanity.com/paper/2407.06190/) (2024)
- [Mask4Former: Mask Transformer for 4D Panoptic Segmentation](https://mlsanity.com/paper/2309.16133/) (2023)
- [DRINet++: Efficient Voxel-as-point Point Cloud Segmentation](https://mlsanity.com/paper/2111.08318/) (2021)
- [Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation](https://mlsanity.com/paper/2202.13377/) (2022)
- [Clustering based Point Cloud Representation Learning for 3D Analysis](https://mlsanity.com/paper/2307.14605/) (2023)
- [MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds](https://mlsanity.com/paper/2307.09316/) (2023)
- [LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels](https://mlsanity.com/paper/2403.15173/) (2024)
- [SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation](https://mlsanity.com/paper/2308.13323/) (2023)
- [MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory](https://mlsanity.com/paper/2311.01556/) (2023)
- [TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2407.09751/) (2024)
- [Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice](https://mlsanity.com/paper/2203.15469/) (2022)
- [Sequential Point Clouds: A Survey](https://mlsanity.com/paper/2204.09337/) (2022)
- [SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud](https://mlsanity.com/paper/2406.16279/) (2024)
- [Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining](https://mlsanity.com/paper/2503.19912/) (2025)
- [Learning Spatial and Temporal Variations for 4D Point Cloud Segmentation](https://mlsanity.com/paper/2207.04673/) (2022)
- [Semantics-Guided Moving Object Segmentation with 3D LiDAR](https://mlsanity.com/paper/2205.03186/) (2022)
- [A survey on deep learning approaches for data integration in autonomous driving system](https://mlsanity.com/paper/2306.11740/) (2023)
- [Point-Plane Projections for Accurate LiDAR Semantic Segmentation in Small Data Scenarios](https://mlsanity.com/paper/2509.10841/) (2025)
- [Deep Sensor Fusion with Pyramid Fusion Networks for 3D Semantic Segmentation](https://mlsanity.com/paper/2205.13629/) (2022)
- [LENet: Lightweight And Efficient LiDAR Semantic Segmentation Using Multi-Scale Convolution Attention](https://mlsanity.com/paper/2301.04275/) (2023)
- [A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distance](https://mlsanity.com/paper/2405.10046/) (2024)
- [4D-CS: Exploiting Cluster Prior for 4D Spatio-Temporal LiDAR Semantic Segmentation](https://mlsanity.com/paper/2501.02937/) (2025)
- [Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation Models](https://mlsanity.com/paper/2608.25418/) (2026)

## Abstract (arXiv)

Understanding and interpreting a 3d environment is a key challenge for autonomous vehicles. Semantic segmentation of 3d point clouds combines 3d information with semantics and thereby provides a valuable contribution to this task. In many real-world applications, point clouds are generated by lidar sensors in a consecutive fashion. Working with a time series instead of single and independent frames enables the exploitation of temporal information. We therefore propose a recurrent segmentation architecture (RNN), which takes a single range image frame as input and exploits recursively aggregated temporal information. An alignment strategy, which we call Temporal Memory Alignment, uses ego motion to temporally align the memory between consecutive frames in feature space. A Residual Network and ConvGRU are investigated for the memory update. We demonstrate the benefits of the presented approach on two large-scale datasets and compare it to several stateof-the-art methods. Our approach ranks first on the SemanticKITTI multiple scan benchmark and achieves state-of-the-art performance on the single scan benchmark. In addition, the evaluation shows that the exploitation of temporal information significantly improves segmentation results compared to a single frame approach.