TY - GEN
T1 - Endo-GSMT
T2 - 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
AU - Gou, Hao
AU - Wang, Changmiao
AU - Yang, Jiahao
AU - Liu, Yaoqun
AU - Jia, Fucang
AU - Xiao, Deqiang
AU - Qin, Feiwei
AU - Luo, Huoling
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - 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.
AB - 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.
KW - 3D Gaussian Splatting
KW - Monocular Dynamic Novel View Synthesis
KW - Surgical Scene Reconstruction
UR - https://www.scopus.com/pages/publications/105017956230
U2 - 10.1007/978-3-032-05114-1_21
DO - 10.1007/978-3-032-05114-1_21
M3 - Conference contribution
AN - SCOPUS:105017956230
SN - 9783032051134
T3 - Lecture Notes in Computer Science
SP - 213
EP - 223
BT - Medical Image Computing and Computer Assisted Intervention, MICCAI 2025 - 28th International Conference, 2025, Proceedings
A2 - Gee, James C.
A2 - Hong, Jaesung
A2 - Sudre, Carole H.
A2 - Golland, Polina
A2 - Park, Jinah
A2 - Alexander, Daniel C.
A2 - Iglesias, Juan Eugenio
A2 - Venkataraman, Archana
A2 - Kim, Jong Hyo
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 23 September 2025 through 27 September 2025
ER -