mlsanityData to 7 Oct 2026

Unsupervised Region-Growing Network for Object Segmentation in Atmospheric Turbulence

arXiv 2311.03572 ↗First posted 6 Nov 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Moving object segmentation in the presence of atmospheric turbulence is highly challenging due to turbulence-induced irregular and time-varying distortions. In this paper, we present an unsupervised approach for segmenting moving objects in videos downgraded by atmospheric turbulence. Our key approach is a detect-then-grow scheme: we first identify a small set of moving object pixels with high confidence, then gradually grow a foreground mask from those seeds to segment all moving objects. This method leverages rigid geometric consistency among video frames to disentangle different types of motions, and then uses the Sampson distance to initialize the seedling pixels. After growing per-frame foreground masks, we use spatial grouping loss and temporal consistency loss to further refine the masks in order to ensure their spatio-temporal consistency. Our method is unsupervised and does not require training on labeled data. For validation, we collect and release the first real-captured long-range turbulent video dataset with ground truth masks for moving objects. Results show that our method achieves good accuracy in segmenting moving objects and is robust for long-range videos with various turbulence strengths.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 69 references that are in the map. First posted on arXiv 6 Nov 2023.

Builds on

31 of 69 references.

References · 31

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2023Segment Anythingcited by 8,158
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  4. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  5. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  6. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  7. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  8. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  9. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  10. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  11. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  12. 2020Video Object Segmentation with Episodic Graph Memory Networkscited by 118
19 more
  1. 2020Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagerycited by 73
  2. 2019Motion Guided Attention for Video Salient Object Detectioncited by 72
  3. 2021Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Datacited by 64
  4. 2022Deformable Sprites for Unsupervised Video Decompositioncited by 61
  5. 2020Making a Case for 3D Convolutions for Object Segmentation in Videoscited by 56
  6. 2016Learning Motion Patterns in Videoscited by 53
  7. 2019Anchor Diffusion for Unsupervised Video Object Segmentationcited by 50
  8. 2021Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transformcited by 50
  9. 2022Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentationcited by 37
  10. 2022Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Modelcited by 37
  11. 2022Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentationcited by 35
  12. 2020F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentationcited by 32
  13. 2022Imaging through the Atmosphere using Turbulence Mitigation Transformercited by 31
  14. 2020Image Reconstruction of Static and Dynamic Scenes through Anisoplanatic Turbulencecited by 30
  15. 2022Unsupervised Video Object Segmentation via Prototype Memory Networkcited by 30
  16. 2019Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenescited by 29
  17. 2017Optical Flow in Mostly Rigid Scenescited by 20
  18. 2020DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detectioncited by 8
  19. 2023SortedAP: Rethinking evaluation metrics for instance segmentationcited by 8

Built on by

Not cited yet.