mlsanityData to 14 Oct 2026

SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion

arXiv 2306.15349 ↗First posted 27 Jun 2023cs.CV cs.AIcited by 30

Not on the map. Why?

Abstract (arXiv)

Semantic scene completion (SSC) jointly predicts the semantics and geometry of the entire 3D scene, which plays an essential role in 3D scene understanding for autonomous driving systems. SSC has achieved rapid progress with the help of semantic context in segmentation. However, how to effectively exploit the relationships between the semantic context in semantic segmentation and geometric structure in scene completion remains under exploration. In this paper, we propose to solve outdoor SSC from the perspective of representation separation and BEV fusion. Specifically, we present the network, named SSC-RS, which uses separate branches with deep supervision to explicitly disentangle the learning procedure of the semantic and geometric representations. And a BEV fusion network equipped with the proposed Adaptive Representation Fusion (ARF) module is presented to aggregate the multi-scale features effectively and efficiently. Due to the low computational burden and powerful representation ability, our model has good generality while running in real-time. Extensive experiments on SemanticKITTI demonstrate our SSC-RS achieves state-of-the-art performance.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

32 of 43 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  4. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  5. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  6. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  7. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  8. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  9. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  10. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
  11. 2020Anisotropic Convolutional Networks for 3D Semantic Scene Completioncited by 127
  12. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
20 more
  1. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  2. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  3. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  4. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  5. 2020Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Datacited by 74
  6. 2019Efficient Semantic Scene Completion Network with Spatial Group Convolutioncited by 66
  7. 2022Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmapcited by 59
  8. 2019SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Drivingcited by 57
  9. 2019RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completioncited by 55
  10. 2021Semantic Scene Completion via Integrating Instances and Scene in-the-Loopcited by 55
  11. 2018Two Stream 3D Semantic Scene Completioncited by 48
  12. 2021View-Guided Point Cloud Completioncited by 46
  13. 2020Depth Based Semantic Scene Completion with Position Importance Aware Losscited by 37
  14. 2021Semantic Segmentation-assisted Scene Completion for LiDAR Point Cloudscited by 37
  15. 2019ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Imagecited by 32
  16. 2020Attention-based Multi-modal Fusion Network for Semantic Scene Completioncited by 28
  17. 2021Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspectivecited by 22
  18. 2022Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentationcited by 22
  19. 2022CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusioncited by 11
  20. 20203D Gated Recurrent Fusion for Semantic Scene Completioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 8; 2026: 9.

30 papers.

Sort:

By area:

  1. 2024DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Drivingcited by 98
  2. 2024Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Drivingcited by 69
  3. 2024Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Predictioncited by 48
  4. 2023Camera-based 3D Semantic Scene Completion with Sparse Guidance Networkcited by 40
  5. 2024OccMamba: Semantic Occupancy Prediction with State Space Modelscited by 30
  6. 2024LiCROcc: Teach Radar for Accurate Semantic Occupancy Prediction using LiDAR and Cameracited by 19
  7. 2024SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIscited by 14
  8. 2025GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attentioncited by 14
  9. 2024Label-efficient Semantic Scene Completion with Scribble Annotationscited by 9
  10. 2024OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexitycited by 9
  11. 2025L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Modelcited by 8
  12. 2025OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Cameracited by 8
18 more
  1. 2025Towards Learning to Complete Anything in Lidarcited by 7
  2. 2024ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learningcited by 6
  3. 2024Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidancecited by 5
  4. 2026GaussianOcc3D: A Gaussian-Based Adaptive Multi-modal 3D Occupancy Predictioncited by 5
  5. 2025Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Modelscited by 3
  6. 2024OMEGA: Efficient Occlusion-Aware Navigation for Air-Ground Robot in Dynamic Environments via State Space Modelcited by 2
  7. 2025Vision-based 3D Semantic Scene Completion via Capture Dynamic Representationscited by 2
  8. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  9. 2026VLMFusionOcc3D: VLM Assisted Multi-Modal 3D Semantic Occupancy Predictioncited by 2
  10. 2026Exploring Easy Boosts for Lidar Semantic Scene Completioncited by 2
  11. 2024VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Predictioncited by 1
  12. 2025TACOcc:Target-Adaptive Cross-Modal Fusion with Volume Rendering for 3D Semantic Occupancycited by 0
  13. 2026Multi-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completioncited by 0
  14. 2026Semantic Occupancy Prediction with Dual Range-Voxel Representationcited by 0
  15. 2026Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Computecited by 0
  16. 2026Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecastingcited by 0
  17. 2026Generative Semantic Scene Completioncited by 0
  18. 2026SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completioncited by 0