collaborators

12 papers

cs.CV2025

InfoMotion: A Graph-Based Approach to Video Dataset Distillation for Echocardiography

Zhe Li, Hadrien Reynaud, Alberto Gomez +1

Echocardiography plays a critical role in the diagnosis and monitoring of cardiovascular diseases as a non-invasive real-time assessment of cardiac structure and function. However,…

cs.CV2025

Label-free Motion-Conditioned Diffusion Model for Cardiac Ultrasound Synthesis

Zhe Li, Hadrien Reynaud, Johanna P Müller +1

Ultrasound echocardiography is essential for the non-invasive, real-time assessment of cardiac function, but the scarcity of labelled data, driven by privacy restrictions and the c…

cs.CV2025

Leveraging Multi-Modal Information to Enhance Dataset Distillation

Zhe Li, Hadrien Reynaud, Bernhard Kainz

Dataset distillation aims to create a small and highly representative synthetic dataset that preserves the essential information of a larger real dataset. Beyond reducing storage a…

cs.CV2025

Video Dataset Condensation with Diffusion Models

Zhe Li, Hadrien Reynaud, Mischa Dombrowski +3

In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, bot…

cs.CV2025

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit +7

Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architect…

cs.CV2025

CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis

Jiayi Wang, Hadrien Reynaud, Franciskus Xaverius Erick +1

Generative modelling of entire CT volumes conditioned on clinical reports has the potential to accelerate research through data augmentation, privacy-preserving synthesis and reduc…