Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.06037 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916386753740800 |
|---|---|
| author | Hayoz, Michel Hahne, Christopher Kurmann, Thomas Allan, Max Beldi, Guido Candinas, Daniel Márquez-Neila, ablo Sznitman, Raphael |
| author_facet | Hayoz, Michel Hahne, Christopher Kurmann, Thomas Allan, Max Beldi, Guido Candinas, Daniel Márquez-Neila, ablo Sznitman, Raphael |
| contents | 3D scene reconstruction from stereo endoscopic video data is crucial for advancing surgical interventions. In this work, we present an online framework for online, dense 3D scene reconstruction and tracking, aimed at enhancing surgical scene understanding and assisting interventions. Our method dynamically extends a canonical scene representation using Gaussian splatting, while modeling tissue deformations through a sparse set of control points. We introduce an efficient online fitting algorithm that optimizes the scene parameters, enabling consistent tracking and accurate reconstruction. Through experiments on the StereoMIS dataset, we demonstrate the effectiveness of our approach, outperforming state-of-the-art tracking methods and achieving comparable performance to offline reconstruction techniques. Our work enables various downstream applications thus contributing to advancing the capabilities of surgical assistance systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_06037 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Online 3D reconstruction and dense tracking in endoscopic videos Hayoz, Michel Hahne, Christopher Kurmann, Thomas Allan, Max Beldi, Guido Candinas, Daniel Márquez-Neila, ablo Sznitman, Raphael Computer Vision and Pattern Recognition 3D scene reconstruction from stereo endoscopic video data is crucial for advancing surgical interventions. In this work, we present an online framework for online, dense 3D scene reconstruction and tracking, aimed at enhancing surgical scene understanding and assisting interventions. Our method dynamically extends a canonical scene representation using Gaussian splatting, while modeling tissue deformations through a sparse set of control points. We introduce an efficient online fitting algorithm that optimizes the scene parameters, enabling consistent tracking and accurate reconstruction. Through experiments on the StereoMIS dataset, we demonstrate the effectiveness of our approach, outperforming state-of-the-art tracking methods and achieving comparable performance to offline reconstruction techniques. Our work enables various downstream applications thus contributing to advancing the capabilities of surgical assistance systems. |
| title | Online 3D reconstruction and dense tracking in endoscopic videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.06037 |