Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Rulin, He, Wenlong, Wang, An, Yao, Qiqi, Hu, Haijun, Wang, Jiankun, Ren, Xi Zhang an Hongliang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.22394
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917969628495872
author Zhou, Rulin
He, Wenlong
Wang, An
Yao, Qiqi
Hu, Haijun
Wang, Jiankun
Ren, Xi Zhang an Hongliang
author_facet Zhou, Rulin
He, Wenlong
Wang, An
Yao, Qiqi
Hu, Haijun
Wang, Jiankun
Ren, Xi Zhang an Hongliang
contents Accurate tissue point tracking in endoscopic videos is critical for robotic-assisted surgical navigation and scene understanding, but remains challenging due to complex deformations, instrument occlusion, and the scarcity of dense trajectory annotations. Existing methods struggle with long-term tracking under these conditions due to limited feature utilization and annotation dependence. We present Endo-TTAP, a novel framework addressing these challenges through: (1) A Multi-Facet Guided Attention (MFGA) module that synergizes multi-scale flow dynamics, DINOv2 semantic embeddings, and explicit motion patterns to jointly predict point positions with uncertainty and occlusion awareness; (2) A two-stage curriculum learning strategy employing an Auxiliary Curriculum Adapter (ACA) for progressive initialization and hybrid supervision. Stage I utilizes synthetic data with optical flow ground truth for uncertainty-occlusion regularization, while Stage II combines unsupervised flow consistency and semi-supervised learning with refined pseudo-labels from off-the-shelf trackers. Extensive validation on two MICCAI Challenge datasets and our collected dataset demonstrates that Endo-TTAP achieves state-of-the-art performance in tissue point tracking, particularly in scenarios characterized by complex endoscopic conditions. The source code and dataset will be available at https://anonymous.4open.science/r/Endo-TTAP-36E5.
format Preprint
id arxiv_https___arxiv_org_abs_2503_22394
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Endo-TTAP: Robust Endoscopic Tissue Tracking via Multi-Facet Guided Attention and Hybrid Flow-point Supervision
Zhou, Rulin
He, Wenlong
Wang, An
Yao, Qiqi
Hu, Haijun
Wang, Jiankun
Ren, Xi Zhang an Hongliang
Computer Vision and Pattern Recognition
Artificial Intelligence
Accurate tissue point tracking in endoscopic videos is critical for robotic-assisted surgical navigation and scene understanding, but remains challenging due to complex deformations, instrument occlusion, and the scarcity of dense trajectory annotations. Existing methods struggle with long-term tracking under these conditions due to limited feature utilization and annotation dependence. We present Endo-TTAP, a novel framework addressing these challenges through: (1) A Multi-Facet Guided Attention (MFGA) module that synergizes multi-scale flow dynamics, DINOv2 semantic embeddings, and explicit motion patterns to jointly predict point positions with uncertainty and occlusion awareness; (2) A two-stage curriculum learning strategy employing an Auxiliary Curriculum Adapter (ACA) for progressive initialization and hybrid supervision. Stage I utilizes synthetic data with optical flow ground truth for uncertainty-occlusion regularization, while Stage II combines unsupervised flow consistency and semi-supervised learning with refined pseudo-labels from off-the-shelf trackers. Extensive validation on two MICCAI Challenge datasets and our collected dataset demonstrates that Endo-TTAP achieves state-of-the-art performance in tissue point tracking, particularly in scenarios characterized by complex endoscopic conditions. The source code and dataset will be available at https://anonymous.4open.science/r/Endo-TTAP-36E5.
title Endo-TTAP: Robust Endoscopic Tissue Tracking via Multi-Facet Guided Attention and Hybrid Flow-point Supervision
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.22394