mlsanityData to 14 Oct 2026

Enhancing 3D Semantic Scene Completion with a Refinement Module

arXiv 2512.18363 ↗First posted 20 Dec 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We propose ESSC-RM, a plug-and-play Enhancing framework for Semantic Scene Completion with a Refinement Module, which can be seamlessly integrated into existing SSC models. ESSC-RM operates in two phases: a baseline SSC network first produces a coarse voxel prediction, which is subsequently refined by a 3D U-Net-based Prediction Noise-Aware Module (PNAM) and Voxel-level Local Geometry Module (VLGM) under multiscale supervision. Experiments on SemanticKITTI show that ESSC-RM consistently improves semantic prediction performance. When integrated into CGFormer and MonoScene, the mean IoU increases from 16.87% to 17.27% and from 11.08% to 11.51%, respectively. These results demonstrate that ESSC-RM serves as a general refinement framework applicable to a wide range of SSC models.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 80 of its 103 references that are in the map. First posted on arXiv 20 Dec 2025.

Builds on

80 of 103 references.

References · 80

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2023Segment Anythingcited by 8,234
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  10. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  11. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  12. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
38 more
  1. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  2. 2017Decoupled Weight Decay Regularizationcited by 1,831
  3. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  7. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  8. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  9. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  11. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 798
  12. 2022Language-driven Semantic Segmentationcited by 717
  13. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  14. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  15. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  16. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  17. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  18. 2018Pyramid Stereo Matching Networkcited by 489
  19. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  20. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  21. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  22. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  23. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 379
  24. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  25. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  26. 2024Long-CLIP: Unlocking the Long-Text Capability of CLIPcited by 300
  27. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 293
  28. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 278
  29. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 252
  30. 2022Neighborhood Attention Transformercited by 239
  31. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 223
  32. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 199
  33. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  34. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 188
  35. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  36. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  37. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  38. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Computecited by 0
  2. 2026Generative Semantic Scene Completioncited by 0
  3. 2026VoxelFix: Post-Hoc Semantic Correction of Completed 3D Voxel Mapscited by 0