mlsanityData to 14 Oct 2026

Scene-Centric Unsupervised Panoptic Segmentation

arXiv 2504.01955 ↗First posted 2 Apr 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene understanding, we eliminate the need for object-centric training data, enabling the unsupervised understanding of complex scenes. To that end, we present the first unsupervised panoptic method that directly trains on scene-centric imagery. In particular, we propose an approach to obtain high-resolution panoptic pseudo labels on complex scene-centric data, combining visual representations, depth, and motion cues. Utilizing both pseudo-label training and a panoptic self-training strategy yields a novel approach that accurately predicts panoptic segmentation of complex scenes without requiring any human annotations. Our approach significantly improves panoptic quality, e.g., surpassing the recent state of the art in unsupervised panoptic segmentation on Cityscapes by 9.4% points in PQ.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 79 of its 93 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

79 of 93 references.

References · 79

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2023Segment Anythingcited by 8,234
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  9. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  10. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  11. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  12. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
38 more
  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  2. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  3. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  4. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  6. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  8. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  9. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  10. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  11. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  12. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  13. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  14. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  15. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  16. 2018Panoptic Segmentationcited by 802
  17. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  18. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  19. 2019Panoptic Feature Pyramid Networkscited by 645
  20. 2019Self-labelling via simultaneous clustering and representation learningcited by 528
  21. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  22. 2019Panoptic-DeepLabcited by 363
  23. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  24. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 232
  25. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  26. 2019MOTS: Multi-Object Tracking and Segmentationcited by 223
  27. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  28. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  29. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  30. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 187
  31. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 174
  32. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  33. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  34. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 148
  35. 2023Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusioncited by 131
  36. 2020What Matters in Unsupervised Optical Flowcited by 124
  37. 2022VICRegL: Self-Supervised Learning of Local Visual Featurescited by 118
  38. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 113

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 7.

10 papers.

  1. 2025Feed-Forward SceneDINO for Unsupervised Semantic Scene Completioncited by 13
  2. 2026INSID3: Training-Free In-Context Segmentation with DINOv3cited by 12
  3. 2025Motion-Refined DINOSAUR for Unsupervised Multi-Object Discoverycited by 4
  4. 2026Scene-Centric Unsupervised Video Panoptic Segmentationcited by 1
  5. 2026Unlocking Diffusion Hierarchies: Adaptive Timestep Selection for Zero-Shot Segmentationcited by 1
  6. 2025S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentationcited by 0
  7. 2026SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoringcited by 0
  8. 2026WiFlow: Estimating Optical Flow using WiFi Channel State Informationcited by 0
  9. 2026FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentationcited by 0
  10. 2026ProGuT: Label-Efficient Panoptic Segmentation for Forest Scenescited by 0