Mesh4D: A Motion-Aware Multi-view Variational Autoencoder for 3D+t Mesh Reconstruction
Qiao M, Zheng J, Zhang W, Ma Q, Li L, Kainz B, O’Regan DP, Matthews PM, Niederer S, Bai W (2026)
Publication Type: Conference contribution
Publication year: 2026
Journal
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 15975 LNCS
Pages Range: 343-353
Conference Proceedings Title: Lecture Notes in Computer Science
Event location: Daejeon, KOR
ISBN: 9783032053244
DOI: 10.1007/978-3-032-05325-1_33
Abstract
Reconstructing temporally coherent 3D meshes of the beating heart from multi-view MR images is an important but challenging problem. The challenge is entangled by the complexity in integrating multi-view data, the sparse coverage of a 3D geometry by 2D image slices, and the interplay between geometry and motion. Current approaches often treat mesh reconstruction and motion estimation as two separate problems. Here we propose Mesh4D, a novel motion-aware method that jointly learns cardiac shape and motion, directly from multi-view MR image sequences. The method introduces three key innovations: (1) A cross-attention encoder that fuses multi-view image information, (2) A transformer-based variational autoencoder (VAE) that jointly model the image feature and motion, and (3) A deformation decoder that generates continuous deformation fields and temporally smooth 3D+t cardiac meshes. Incorporating geometric regularisation and motion consistency constraints, Mesh4D can reconstruct high-quality 3D+t meshes (7,698 vertices, 15,384 faces) of the heart ventricles across 50 time frames, within less than 3 s. When compared to existing approaches, Mesh4D achieves notable improvements in reconstruction accuracy and motion smoothness, offering an efficient image-to-mesh solution for quantifying shape and motion of the heart and creating digital heart models.
Authors with CRIS profile
Involved external institutions
University College London (UCL)
United Kingdom (GB)
Imperial College London / The Imperial College of Science, Technology and Medicine
United Kingdom (GB)
United Kingdom (GB)
Imperial College London / The Imperial College of Science, Technology and Medicine
United Kingdom (GB)
How to cite
APA:
Qiao, M., Zheng, J., Zhang, W., Ma, Q., Li, L., Kainz, B.,... Bai, W. (2026). Mesh4D: A Motion-Aware Multi-view Variational Autoencoder for 3D+t Mesh Reconstruction. In James C. Gee, Jaesung Hong, Carole H. Sudre, Polina Golland, Jinah Park, Daniel C. Alexander, Juan Eugenio Iglesias, Archana Venkataraman, Jong Hyo Kim (Eds.), Lecture Notes in Computer Science (pp. 343-353). Daejeon, KOR: Springer Science and Business Media Deutschland GmbH.
MLA:
Qiao, Mengyun, et al. "Mesh4D: A Motion-Aware Multi-view Variational Autoencoder for 3D+t Mesh Reconstruction." Proceedings of the 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025, Daejeon, KOR Ed. James C. Gee, Jaesung Hong, Carole H. Sudre, Polina Golland, Jinah Park, Daniel C. Alexander, Juan Eugenio Iglesias, Archana Venkataraman, Jong Hyo Kim, Springer Science and Business Media Deutschland GmbH, 2026. 343-353.
BibTeX: Download