3-D Reconstruction from consecutive endoscopic images using Gaussian Splatting

Hung-Le Minh, Duy-Van Truong, Huy-Xuan Manh, Viet-Hang Dao, Phuc-Binh Nguyen, Thanh-Tung Nguyen, Hai-Vu; Proceedings of the Asian Conference on Computer Vision (ACCV) Workshops, 2024, pp. 482-494

Abstract

Recent advancements in 3D reconstruction helped endoscopy doctors analyze the patients' gastrointestinal surfaces and abnormality detections. In this work, we expand this development further with a reconstruction method based on both classic techniques like structure from motion and recent advanced techniques like neural radiation fields and Gaussian splatting with new Gaussian encoding-decoding modules. In addition, an unique dataset was collected with some videos from daily endoscopy examinations. This development helped us achieve better reconstruction results and lower training time compared to existing methods.

Related Material

[pdf]
[bibtex]
@InProceedings{Minh_2024_ACCV, author = {Minh, Hung-Le and Truong, Duy-Van and Manh, Huy-Xuan and Dao, Viet-Hang and Nguyen, Phuc-Binh and Nguyen, Thanh-Tung and Hai-Vu}, title = {3-D Reconstruction from consecutive endoscopic images using Gaussian Splatting}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV) Workshops}, month = {December}, year = {2024}, pages = {482-494} }