mlsanityData to 7 Oct 2026

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

arXiv 2306.09347 ↗First posted 15 Jun 2023cs.CV cs.LG cs.ROcited by 123

Not on the map. Why?

Abstract (arXiv)

Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a novel framework that harnesses VFMs for segmenting diverse automotive point cloud sequences. Seal exhibits three appealing properties: i) Scalability: VFMs are directly distilled into point clouds, obviating the need for annotations in either 2D or 3D during pretraining. ii) Consistency: Spatial and temporal relationships are enforced at both the camera-to-LiDAR and point-to-segment regularization stages, facilitating cross-modal representation learning. iii) Generalizability: Seal enables knowledge transfer in an off-the-shelf manner to downstream tasks involving diverse point clouds, including those from real/synthetic, low/high-resolution, large/small-scale, and clean/corrupted datasets. Extensive experiments conducted on eleven different point cloud datasets showcase the effectiveness and superiority of Seal. Notably, Seal achieves a remarkable 45.0% mIoU on nuScenes after linear probing, surpassing random initialization by 36.9% mIoU and outperforming prior arts by 6.1% mIoU. Moreover, Seal demonstrates significant performance gains over existing methods across 20 different few-shot fine-tuning tasks on all eleven tested point cloud datasets.

Key facts. Cited by 123 papers in the map (data through 7 Oct 2026). Builds on 100 of its 122 references that are in the map. First posted on arXiv 15 Jun 2023.

Builds on

100 of 122 references.

References · 100

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2023Segment Anythingcited by 8,158
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  10. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  11. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  12. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
38 more
  1. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  2. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  4. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  5. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  6. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  9. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  10. 2016Colorful Image Colorizationcited by 1,113
  11. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  12. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  13. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  14. 2023Segment Everything Everywhere All at Oncecited by 546
  15. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  16. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  17. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  18. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  19. 2020Understanding the Behaviour of Contrastive Losscited by 397
  20. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  21. 2022Scaling Language-Image Pre-training via Maskingcited by 317
  22. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  23. 2022Generalized Decoding for Pixel, Image, and Languagecited by 292
  24. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  25. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  26. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  27. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  28. 2023A Simple Framework for Open-Vocabulary Segmentation and Detectioncited by 197
  29. 2023SegGPT: Segmenting Everything In Contextcited by 193
  30. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  31. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  32. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  33. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  34. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  35. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  36. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
  37. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  38. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150

50 most cited of 100 All 100 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 39; 2025: 50; 2026: 21.

123 papers.

Sort:

By area:

  1. 2023LangSplat: 3D Language Gaussian Splattingcited by 410
  2. 20243D Gaussian as a New Era: A Surveycited by 102
  3. 2024SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Groundingcited by 66
  4. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  5. 2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detectioncited by 57
  6. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  7. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  8. 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobilitycited by 48
  9. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 47
  10. 2024Better Call SAL: Towards Learning to Segment Anything in Lidarcited by 47
  11. 2023SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentationcited by 44
  12. 2023Three Pillars improving Vision Foundation Model Distillation for Lidarcited by 43
38 more
  1. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 39
  2. 2024OpenESS: Event-based Semantic Scene Understanding with Open Vocabulariescited by 37
  3. 2024SegPoint: Segment Any Point Cloud via Large Language Modelcited by 34
  4. 2024PTQ4SAM: Post-Training Quantization for Segment Anythingcited by 32
  5. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  6. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  7. 2025DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentationcited by 31
  8. 2023PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillationcited by 27
  9. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
  10. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  11. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  12. 2024Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environmentscited by 21
  13. 2023Learning to Adapt SAM for Segmenting Cross-domain Point Cloudscited by 20
  14. 2025LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenescited by 19
  15. 2024OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networkscited by 17
  16. 2024GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistencycited by 17
  17. 2025MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentationcited by 16
  18. 2025PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Drivingcited by 16
  19. 2025Perspective-Invariant 3D Object Detectioncited by 16
  20. 2024Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 15
  21. 2024RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentationcited by 15
  22. 2023Applications of Large Scale Foundation Models for Autonomous Drivingcited by 14
  23. 2024Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3Dcited by 14
  24. 2025LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequencescited by 14
  25. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
  26. 2023TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentationcited by 13
  27. 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learningcited by 13
  28. 2025RefAV: Towards Planning-Centric Scenario Miningcited by 13
  29. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
  30. 2024Part2Object: Hierarchical Unsupervised 3D Instance Segmentationcited by 12
  31. 2025SafeMap: Robust HD Map Construction from Incomplete Observationscited by 12
  32. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  33. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  34. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understandingcited by 10
  35. 2023When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation with Weak-and-Noisy Supervisioncited by 9
  36. 2024MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detectioncited by 9
  37. 2024Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detectioncited by 9
  38. 2024Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perceptioncited by 8

50 most cited of 123 All 123 (JSON)