-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2025_CVPR, author = {Wu, Chun-Hung and Chen, Shih-Hong and Hu, Chih-Yao and Wu, Hsin-Yu and Chen, Kai-Hsin and Chen, Yu-You and Su, Chih-Hai and Lee, Chih-Kuo and Liu, Yu-Lun}, title = {DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {15682-15692} }
DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation
Abstract
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. Please see our project page at kirito878.github.io/DeNVeR.
Related Material