VecHeart: Holistic Four-Chamber Cardiac Anatomy Modeling via Hybrid VecSets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yihong, Fua, Pascal
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910153599614976
author Chen, Yihong
Fua, Pascal
author_facet Chen, Yihong
Fua, Pascal
contents Accurate cardiac anatomy modeling requires the model to be able to handle intricate interrelations among structures. In this paper, we propose VecHeart, a unified framework for holistic reconstruction and generation of four-chamber cardiac structures. To overcome the limitations of current feed-forward implicit methods, specifically their restriction to single-object modeling and their neglect of inter-part correlations, we introduce Hybrid Part Transformer, which leverages part-specific learnable queries and interleaved attention to capture complex inter-chamber dependencies. Furthermore, we propose Anatomical Completion Masking and Modality Alignment strategies, enabling the model to infer complete four-chamber structures from partial, sparse, or noisy observations, even when certain anatomical parts are entirely missing. VecHeart also seamlessly extends to 3D+t dynamic mesh sequence generation, demonstrating exceptional versatility. Experiments show that our method achieves state-of-the-art performance, maintaining high-fidelity reconstruction across diverse challenging scenarios. Code will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19403
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VecHeart: Holistic Four-Chamber Cardiac Anatomy Modeling via Hybrid VecSets
Chen, Yihong
Fua, Pascal
Computer Vision and Pattern Recognition
Accurate cardiac anatomy modeling requires the model to be able to handle intricate interrelations among structures. In this paper, we propose VecHeart, a unified framework for holistic reconstruction and generation of four-chamber cardiac structures. To overcome the limitations of current feed-forward implicit methods, specifically their restriction to single-object modeling and their neglect of inter-part correlations, we introduce Hybrid Part Transformer, which leverages part-specific learnable queries and interleaved attention to capture complex inter-chamber dependencies. Furthermore, we propose Anatomical Completion Masking and Modality Alignment strategies, enabling the model to infer complete four-chamber structures from partial, sparse, or noisy observations, even when certain anatomical parts are entirely missing. VecHeart also seamlessly extends to 3D+t dynamic mesh sequence generation, demonstrating exceptional versatility. Experiments show that our method achieves state-of-the-art performance, maintaining high-fidelity reconstruction across diverse challenging scenarios. Code will be released.
title VecHeart: Holistic Four-Chamber Cardiac Anatomy Modeling via Hybrid VecSets
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.19403