mlsanityData to 7 Oct 2026

DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation

arXiv 2406.01591 ↗First posted 3 Jun 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

This paper presents Deformable Neural Vessel Representations (DeNVeR), an unsupervised approach for vessel segmentation in X-ray angiography videos without annotated ground truth. DeNVeR utilizes optical flow and layer separation techniques, enhancing segmentation accuracy and adaptability through test-time training. Key contributions include a novel layer separation bootstrapping technique, a parallel vessel motion loss, and the integration of Eulerian motion fields for modeling complex vessel dynamics. A significant component of this research is the introduction of the XACV dataset, the first X-ray angiography coronary video dataset with high-quality, manually labeled segmentation ground truth. Extensive evaluations on both XACV and CADICA datasets demonstrate that DeNVeR outperforms current state-of-the-art methods in vessel segmentation accuracy and generalization capability while maintaining temporal coherency.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 42 of its 78 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

42 of 78 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  6. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  7. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  8. 2017Deep Image Priorcited by 1,097
  9. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  10. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  11. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  12. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
30 more
  1. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  2. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  3. 2020clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentationcited by 286
  4. 2020Contrastive Clusteringcited by 264
  5. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  6. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  7. 2023Robust Dynamic Radiance Fieldscited by 193
  8. 2017Colorization as a Proxy Task for Visual Understandingcited by 175
  9. 2020SpeedNet: Learning the Speediness in Videoscited by 171
  10. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  11. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  12. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  13. 2019Unsupervised Object Segmentation by Redrawingcited by 74
  14. 2019Unsupervised Moving Object Detection via Contextual Information Separationcited by 72
  15. 2022Deformable Sprites for Unsupervised Video Decompositioncited by 61
  16. 2023Understanding metric-related pitfalls in image analysis validationcited by 57
  17. 2017Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagerycited by 56
  18. 2022Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentationcited by 55
  19. 2020Animating Pictures with Eulerian Motion Fieldscited by 54
  20. 2021Labels4Free: Unsupervised Segmentation using StyleGANcited by 53
  21. 2020Learning to See Through Obstructionscited by 38
  22. 2021Clustering by Maximizing Mutual Information Across Viewscited by 23
  23. 2021Hybrid Neural Fusion for Full-frame Video Stabilizationcited by 21
  24. 2020Learning to See Through Obstructions with Layered Decompositioncited by 20
  25. 2022ContrastMask: Contrastive Learning to Segment Every Thingcited by 19
  26. 2021Neural Image Representations for Multi-Image Fusion and Layer Separationcited by 18
  27. 2021Sequential vessel segmentation via deep channel attention networkcited by 14
  28. 2024CADICA: a new dataset for coronary artery disease detection by using invasive coronary angiographycited by 11
  29. 2019Accurate Retinal Vessel Segmentation via Octave Convolution Neural Networkcited by 4
  30. 2023FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 8.

13 papers.

Sort:

By area:

  1. 2024SpectroMotion: Dynamic 3D Reconstruction of Specular Scenescited by 21
  2. 20263AM: 3egment Anything with Geometric Consistency in Videoscited by 3
  3. 2025Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutionscited by 2
  4. 2025VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentationcited by 2
  5. 2026FMS2: Unified Flow Matching for Segmentation and Synthesis of Thin Structurescited by 2
  6. 2026Few-Shot Video Object Segmentation in X-Ray Angiography Using Local Matching and Spatio-Temporal Consistency Losscited by 1
  7. 2025TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracingcited by 0
  8. 2025From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fieldscited by 0
  9. 2026Vascular anatomy-aware self-supervised pre-training for X-ray angiogram analysiscited by 0
  10. 2026Uncertainty-Aware Concept and Motion Segmentation for Semi-Supervised Angiography Videoscited by 0
  11. 2026TubeMLLM: A Foundation Model for Topology Knowledge Exploration in Vessel-like Anatomycited by 0
  12. 2026MoE-based Feature Adapter for Prompt-free Binary Coronary Artery Segmentation in X-ray Angiographycited by 0
1 more
  1. 2026ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentationcited by 0