mlsanityData to 7 Oct 2026

Multi-Object Discovery by Low-Dimensional Object Motion

arXiv 2307.08027 ↗First posted 16 Jul 2023cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Recent work in unsupervised multi-object segmentation shows impressive results by predicting motion from a single image despite the inherent ambiguity in predicting motion without the next image. On the other hand, the set of possible motions for an image can be constrained to a low-dimensional space by considering the scene structure and moving objects in it. We propose to model pixel-wise geometry and object motion to remove ambiguity in reconstructing flow from a single image. Specifically, we divide the image into coherently moving regions and use depth to construct flow bases that best explain the observed flow in each region. We achieve state-of-the-art results in unsupervised multi-object segmentation on synthetic and real-world datasets by modeling the scene structure and object motion. Our evaluation of the predicted depth maps shows reliable performance in monocular depth estimation.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 54 of its 71 references that are in the map. First posted on arXiv 16 Jul 2023.

Builds on

54 of 71 references.

References · 54

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2017Mask R-CNNcited by 7,259
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  6. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  8. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  9. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  10. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  11. 2020Object-Centric Learning with Slot Attentioncited by 865
  12. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
38 more
  1. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  2. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  3. 2022Kubric: A scalable dataset generatorcited by 373
  4. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  5. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  6. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  7. 2017Sparsity Invariant CNNscited by 325
  8. 2021Conditional Object-Centric Learning from Videocited by 247
  9. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  10. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  11. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  12. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
  13. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  14. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  15. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  16. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  17. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  18. 2019SCALOR: Generative World Models with Scalable Object Representationscited by 108
  19. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  20. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  21. 2019Unsupervised Moving Object Detection via Contextual Information Separationcited by 72
  22. 2016It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videoscited by 71
  23. 2021SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decompositioncited by 69
  24. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  25. 2020Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentationcited by 62
  26. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  27. 2020Generative Neurosymbolic Machinescited by 57
  28. 2016Learning Motion Patterns in Videoscited by 53
  29. 2019Towards Segmenting Anything That Movescited by 51
  30. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  31. 2021The Emergence of Objectness: Learning Zero-Shot Segmentation from Videoscited by 45
  32. 2022Discovering Objects that Can Movecited by 44
  33. 2022Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motioncited by 42
  34. 2017Learning to Segment Moving Objectscited by 39
  35. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  36. 2021MarioNette: Self-Supervised Sprite Learningcited by 35
  37. 2018Object Discovery in Videos as Foreground Motion Clusteringcited by 32
  38. 2021Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projectioncited by 28

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 9; 2026: 3.

16 papers.

Sort:

  1. 2024Moving Object Segmentation: All You Need Is SAM (and Flow)cited by 30
  2. 2024Temporally Consistent Object-Centric Learning by Contrasting Slotscited by 30
  3. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  4. 2025Learning segmentation from point trajectoriescited by 14
  5. 2025Predicting Video Slot Attention Queries from Random Slot-Feature Pairscited by 12
  6. 2023Appearance-Based Refinement for Object-Centric Motion Segmentationcited by 11
  7. 2025Scene-Centric Unsupervised Panoptic Segmentationcited by 10
  8. 2025FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Basescited by 10
  9. 2025Motion-Refined DINOSAUR for Unsupervised Multi-Object Discoverycited by 4
  10. 2025FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matchingcited by 2
  11. 2026GMOS: Grounding Moving Object Segmentation in 3D Space and Timecited by 1
  12. 2026Scene-Centric Unsupervised Video Panoptic Segmentationcited by 1
4 more
  1. 2025xMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motioncited by 0
  2. 2025DADO: A Depth-Attention framework for Object Discoverycited by 0
  3. 2025S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentationcited by 0
  4. 2026WiFlow: Estimating Optical Flow using WiFi Channel State Informationcited by 0