mlsanityData to 14 Oct 2026

L2COcc: Lightweight Camera-Centric Semantic Scene Completion via Distillation of LiDAR Model

arXiv 2503.12369 ↗First posted 16 Mar 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Semantic Scene Completion (SSC) constitutes a pivotal element in autonomous driving perception systems, tasked with inferring the 3D semantic occupancy of a scene from sensory data. To improve accuracy, prior research has implemented various computationally demanding and memory-intensive 3D operations, imposing significant computational requirements on the platform during training and testing. This paper proposes L2COcc, a lightweight camera-centric SSC framework that also accommodates LiDAR inputs. With our proposed efficient voxel transformer (EVT) and cross-modal knowledge modules, including feature similarity distillation (FSD), TPV distillation (TPVD) and prediction alignment distillation (PAD), our method substantially reduce computational burden while maintaining high accuracy. The experimental evaluations demonstrate that our proposed method surpasses the current state-of-the-art vision-based SSC methods regarding accuracy on both the SemanticKITTI and SSCBench-KITTI-360 benchmarks, respectively. Additionally, our method is more lightweight, exhibiting a reduction in both memory consumption and inference time by over 23% compared to the current state-of-the-arts method. Code is available at our project page:https://studyingfufu.github.io/L2COcc/.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 30 of its 38 references that are in the map. First posted on arXiv 16 Mar 2025.

Builds on

30 of 38 references.

References · 30

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  5. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  6. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  7. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  8. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  9. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  10. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  11. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  12. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
18 more
  1. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
  2. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 165
  3. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  4. 2023Symphonize 3D Semantic Scene Completion with Contextual Instance Queriescited by 90
  5. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  6. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  7. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 75
  8. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 52
  9. 2024Context and Geometry Aware Voxel Transformer for Semantic Scene Completioncited by 50
  10. 2022Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detectioncited by 48
  11. 2024MonoOcc: Digging into Monocular Semantic Occupancy Predictioncited by 44
  12. 2023UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye Viewcited by 43
  13. 2024Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillationcited by 43
  14. 2023PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awarenesscited by 42
  15. 2023DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillationcited by 41
  16. 2023Camera-based 3D Semantic Scene Completion with Sparse Guidance Networkcited by 40
  17. 2023SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusioncited by 30
  18. 2024LiCROcc: Teach Radar for Accurate Semantic Occupancy Prediction using LiDAR and Cameracited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2025VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detectioncited by 13
  2. 2026Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robotscited by 5
  3. 2026FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Predictioncited by 2
  4. 2026Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Predictioncited by 1
  5. 2026VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understandingcited by 1
  6. 2025HD2-SSC: High-Dimension High-Density Semantic Scene Completion for Autonomous Drivingcited by 0
  7. 2026UnsOcc: 3D Semantic Occupancy Prediction in Unstructured Scene via Rendering Fusioncited by 0
  8. 2026SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completioncited by 0