analiza aiqbench
This research addresses critical limitations in monocular endoscopy by adapting foundation models to ensure geometric consistency, which is essential for reliable depth prediction and pose estimation during image-guided navigation. By introducing a structured adaptation method that couples low-rank adapters with layer-wise training objectives, the framework improves synthetic-to-real transfer across various clinical procedures like bronchoscopy. The work demonstrates that enforcing geometry-aware representations in intermediate features significantly enhances downstream performance on complex medical imaging tasks.
Geometry-Consistent Endoscopic Representations for Image-Guided Navigation via Structured Foundation Model Adaptation
arXiv:2606.17340v1 Announce Type: cross Abstract: Accurate vision-based navigation in monocular endoscopy is difficult due to limited depth cues, weak tissue texture, non-rigid deformation, and substantial appearance variation across domains, all of which complicate pose estimation, depth prediction, and image-to-anatomy alignment. Although recent vision foundation models have shown promise, their learned representations often remain insufficiently geometry-consistent, hindering stable feature correspondence and limiting their reliability for downstream navigation tasks. We propose a unified framework for learning geometry-consistent and domain-robust image representations for monocular endoscopy. The framework combines a synthetic data pipeline that provides accurate geometric supervision with Hierarchy-Aware Geometry-Semantic Adaptation, a structured alternative to standard LoRA that inserts low-rank adapters selectively across the transformer hierarchy and couples them with layer-wise training objectives to encourage geometric correspondence in intermediate features and semantic consistency in deeper features. Experiments on public and proprietary datasets show improved geometric and semantic representation quality, leading to better performance on downstream navigation tasks including pose estimation and monocular depth estimation. The learned representations show favorable synthetic-to-real transfer on clinical bronchoscopy and provide a useful initialization for adaptation to sinus endoscopy and colonoscopy under limited supervision. The framework also shows favorable scaling with model size and training data. These results support hierarchy-aware, geometry-guided adaptation as a practical approach for endoscopic representation learning.
Abstract:Accurate vision-based navigation in monocular endoscopy is difficult due to limited depth cues, weak tissue texture, non-rigid deformation, and substantial appearance variation across domains, all of which complicate pose estimation, depth prediction, and image-to-anatomy alignment. Although recent vision foundation models have shown promise, their learned representations often remain insufficiently geometry-consistent, hindering stable feature correspondence and limiting their reliability for downstream navigation tasks. We propose a unified framework for learning geometry-consistent and domain-robust image representations for monocular endoscopy. The framework combines a synthetic data pipeline that provides accurate geometric supervision with Hierarchy-Aware Geometry-Semantic Adaptation, a structured alternative to standard LoRA that inserts low-rank adapters selectively across the transformer hierarchy and couples them with layer-wise training objectives to encourage geometric correspondence in intermediate features and semantic consistency in deeper features. Experiments on public and proprietary datasets show improved geometric and semantic representation quality, leading to better performance on downstream navigation tasks including pose estimation and monocular depth estimation. The learned representations show favorable synthetic-to-real transfer on clinical bronchoscopy and provide a useful initialization for adaptation to sinus endoscopy and colonoscopy under limited supervision. The framework also shows favorable scaling with model size and training data. These results support hierarchy-aware, geometry-guided adaptation as a practical approach for endoscopic representation learning.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2606.17340 [cs.CV]
(or arXiv:2606.17340v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.17340 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 307 cuvinte
Subiecte conexe
HorizonNav: Geometry-Guided Video Diffusion for Anticipatory 3D Robot Navigation
arXiv · 12 oct. 2026
Automating coherent long-form video generation
Google Research · 24 sept. 2026
A Navigable Manifold of Hypothesized Consciousness-Spectrum States in Language Model Representations
arXiv · 10 iun. 2026
CanonNav: Disentangling Navigation Behavior from Camera Geometry in Cross-Platform Visual Navigation
arXiv · 2 sept. 2026