mlsanityData to 7 Oct 2026

A topological solution to object segmentation and tracking

arXiv 2107.02036 ↗First posted 5 Jul 2021cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The world is composed of objects, the ground, and the sky. Visual perception of objects requires solving two fundamental challenges: segmenting visual input into discrete units, and tracking identities of these units despite appearance changes due to object deformation, changing perspective, and dynamic occlusion. Current computer vision approaches to segmentation and tracking that approach human performance all require learning, raising the question: can objects be segmented and tracked without learning? Here, we show that the mathematical structure of light rays reflected from environment surfaces yields a natural representation of persistent surfaces, and this surface representation provides a solution to both the segmentation and tracking problems. We describe how to generate this surface representation from continuous visual input, and demonstrate that our approach can segment and invariantly track objects in cluttered synthetic video despite severe appearance changes, without requiring learning.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 91 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

26 of 91 references.

References · 26

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  4. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  5. 2019Event-based Vision: A Surveycited by 1,010
  6. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  7. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  8. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  9. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  10. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  11. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 477
  12. 2019Video Object Segmentation using Space-Time Memory Networkscited by 436
14 more
  1. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  2. 2019MOTS: Multi-Object Tracking and Segmentationcited by 222
  3. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  4. 2021How to represent part-whole hierarchies in a neural networkcited by 123
  5. 2019The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentationcited by 95
  6. 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
  7. 2017Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependenciescited by 76
  8. 2020Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentationcited by 62
  9. 2021Out of Distribution Generalization in Machine Learningcited by 59
  10. 2020Learning Physical Graph Representations from Visual Scenescited by 50
  11. 2017Learning to Segment Moving Objectscited by 39
  12. 2018Object Discovery in Videos as Foreground Motion Clusteringcited by 32
  13. 2020Multi-Object Tracking with Siamese Track-RCNNcited by 14
  14. 2020Self-supervised Object Tracking with Cycle-consistent Siamese Networkscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1; 2026: 1.

4 papers.

  1. 2022Unsupervised Segmentation in Real-World Images via Spelke Object Inferencecited by 15
  2. 2024Masked Image Modeling as a Framework for Self-Supervised Learning across Eye Movementscited by 0
  3. 2025Ideal Observer for Segmentation of Dead Leaves Imagescited by 0
  4. 2026QualiaNet: An Experience-Before-Inference Networkcited by 0