mlsanityData to 14 Oct 2026

Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds

arXiv 2109.11453 ↗First posted 23 Sep 2021cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Outdoor scene completion is a challenging issue in 3D scene understanding, which plays an important role in intelligent robotics and autonomous driving. Due to the sparsity of LiDAR acquisition, it is far more complex for 3D scene completion and semantic segmentation. Since semantic features can provide constraints and semantic priors for completion tasks, the relationship between them is worth exploring. Therefore, we propose an end-to-end semantic segmentation-assisted scene completion network, including a 2D completion branch and a 3D semantic segmentation branch. Specifically, the network takes a raw point cloud as input, and merges the features from the segmentation branch into the completion branch hierarchically to provide semantic information. By adopting BEV representation and 3D sparse convolution, we can benefit from the lower operand while maintaining effective expression. Besides, the decoder of the segmentation branch is used as an auxiliary, which can be discarded in the inference stage to save computational consumption. Extensive experiments demonstrate that our method achieves competitive performance on SemanticKITTI dataset with low latency. Code and models will be released at https://github.com/jokester-zzz/SSA-SC.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 24 of its 30 references that are in the map. First posted on arXiv 23 Sep 2021.

Builds on

24 of 30 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  5. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  8. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  9. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  10. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  11. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  12. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
12 more
  1. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
  2. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  3. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  4. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
  5. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  6. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  7. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  8. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  9. 2020Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Datacited by 74
  10. 2019Efficient Semantic Scene Completion Network with Spatial Group Convolutioncited by 66
  11. 2019SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Drivingcited by 57
  12. 2018Two Stream 3D Semantic Scene Completioncited by 48

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 12; 2025: 13; 2026: 6.

37 papers.

Sort:

By area:

  1. 2024DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Drivingcited by 98
  2. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 86
  3. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  4. 2024Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Drivingcited by 69
  5. 2024SemCity: Semantic Scene Generation with Triplane Diffusioncited by 53
  6. 2024Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Predictioncited by 48
  7. 2023Camera-based 3D Semantic Scene Completion with Sparse Guidance Networkcited by 40
  8. 2023SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusioncited by 30
  9. 2024LiCROcc: Teach Radar for Accurate Semantic Occupancy Prediction using LiDAR and Cameracited by 19
  10. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Modelscited by 16
  11. 2025GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attentioncited by 14
  12. 2025VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detectioncited by 13
25 more
  1. 2024Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Drivingcited by 12
  2. 2024TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sightcited by 12
  3. 2025SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completioncited by 9
  4. 2025OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Cameracited by 8
  5. 2024ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learningcited by 6
  6. 2024MetaSSC: Enhancing 3D Semantic Scene Completion for Autonomous Driving through Meta-Learning and Long-sequence Modelingcited by 4
  7. 2024Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completioncited by 4
  8. 2025Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Modelscited by 3
  9. 2025US-X Complete: A Multi-Modal Approach to Anatomical 3D Shape Recoverycited by 3
  10. 2025Enhancing 3D Semantic Scene Completion with a Refinement Modulecited by 3
  11. 2024OMEGA: Efficient Occlusion-Aware Navigation for Air-Ground Robot in Dynamic Environments via State Space Modelcited by 2
  12. 2025Vision-based 3D Semantic Scene Completion via Capture Dynamic Representationscited by 2
  13. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  14. 2026Exploring Easy Boosts for Lidar Semantic Scene Completioncited by 2
  15. 2022Circular Accessible Depth: A Robust Traversability Representation for UGV Navigationcited by 1
  16. 2023MOVES: Movable and Moving LiDAR Scene Segmentation in Label-Free settings using Static Reconstructioncited by 1
  17. 2025DGOcc: Depth-aware Global Query-based Network for Monocular 3D Occupancy Predictioncited by 0
  18. 2025TACOcc:Target-Adaptive Cross-Modal Fusion with Volume Rendering for 3D Semantic Occupancycited by 0
  19. 2025SWA-SOP: Spatially-aware Window Attention for Semantic Occupancy Prediction in Autonomous Drivingcited by 0
  20. 2025Towards Temporal Fusion Beyond the Field of View for Camera-based Semantic Scene Completioncited by 0
  21. 2026Multi-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completioncited by 0
  22. 2026Semantic Occupancy Prediction with Dual Range-Voxel Representationcited by 0
  23. 2026Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecastingcited by 0
  24. 2026Generative Semantic Scene Completioncited by 0
  25. 2026SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completioncited by 0