Endo-GSMT: Endoscopic Monocular Scene Reconstruction with Dynamic Gaussian Splatting and Motion Tracking

  • Hao Gou
  • , Changmiao Wang
  • , Jiahao Yang
  • , Yaoqun Liu
  • , Fucang Jia
  • , Deqiang Xiao
  • , Feiwei Qin*
  • , Huoling Luo*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Limited perspectives and complex tissue deformations pose significant challenges in accurately reconstructing monocular dynamic surgical scene. Many existing methods fail to fully exploit inter-frame relationships, resulting in suboptimal performance in processing complex tissue deformations and synthesizing novel views. To address these challenges, we propose Endo-GSMT, an accurate and high-quality method for dynamic endoscopic reconstruction from monocular surgical videos. Our method begins by comprehensively extracting both intra-frame information and inter-frame relationships from the raw monocular videos. We incorporate monocular depth priors and dense displacement field priors to generate the pixel-wise 3D trajectories during the training phase. Then, we design a set of compact and low-dimensional Sim(3) motion bases, with each point’s motion represented as a weighted combination of these motion bases. Furthermore, we develop a novel depth loss function to address the scale inconsistency inherent in monocular depth priors. We evaluate our method using two distinct evaluation strategies, the experimental results demonstrate that our method achieves state-of-the-art reconstruction quality. The code is available at https://github.com/M11pha/Endo-GSMT.

Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention, MICCAI 2025 - 28th International Conference, 2025, Proceedings
EditorsJames C. Gee, Jaesung Hong, Carole H. Sudre, Polina Golland, Jinah Park, Daniel C. Alexander, Juan Eugenio Iglesias, Archana Venkataraman, Jong Hyo Kim
PublisherSpringer Science and Business Media Deutschland GmbH
Pages213-223
Number of pages11
ISBN (Print)9783032051134
DOIs
Publication statusPublished - 2026
Event28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025 - Daejeon, Korea, Republic of
Duration: 23 Sept 202527 Sept 2025

Publication series

NameLecture Notes in Computer Science
Volume15968 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
Country/TerritoryKorea, Republic of
CityDaejeon
Period23/09/2527/09/25

Keywords

  • 3D Gaussian Splatting
  • Monocular Dynamic Novel View Synthesis
  • Surgical Scene Reconstruction

Fingerprint

Dive into the research topics of 'Endo-GSMT: Endoscopic Monocular Scene Reconstruction with Dynamic Gaussian Splatting and Motion Tracking'. Together they form a unique fingerprint.

Cite this