AI4M3D

About

Workshop Overview

Medical 3D vision lies at the intersection of artificial intelligence, computer vision, computer graphics, and medical imaging. It is becoming increasingly crucial for diagnosis, surgical planning, simulation, and personalised healthcare.

Recent advances in deep learning, generative models, neural rendering, and vision-language approaches have enabled significant progress in 3D reconstruction, 3D generation, novel view synthesis, and the immersive visualization of medical data, including XR-supported applications. This also extends to neuroscience, with approaches that reconstruct 3D representations from neural data.

The goal of this workshop is to highlight innovative, AI-driven techniques for 3D vision in the medical field and encourage discussion about the unique challenges in this field, including data scarcity, noise, anatomical variability, robustness, interpretability, and clinical reliability.

This workshop aims not only to serve as a venue for presenting work in this area but also to build a community and share information in this new field.

Topics

Workshop Topics

We invite original, previously unpublished work addressing, but not limited to, the following topics:

AI for medical 3D reconstruction and neural rendering

3D reconstruction from CT or MRI data
3D Gaussian Splatting for medical scene understanding
Point cloud and mesh reconstruction for surgical planning
Real-time intraoperative 3D rendering
4D dynamic reconstruction from medical images

Generative AI for medical and neural 3D data

3D models generation from EEG or MRI data
3D shape generation and completion for anatomy
Generative AI for 3D medical data synthesis
Neural data-driven 3D brain representation generation
Interactive 3D avatars for medical training

Vision-language models for 3D understanding

Language-promptable 3D segmentation for anatomical structures
Efficient 3D VLM architectures for volumetric data
Multi-modal 3D clinical reasoning and visual question answering
Zero-shot and few-shot 3D understanding via foundation VLMs

XR-supported visualization and simulation

Virtual overlays for intraoperative guidance
XR interfaces for medical education and surgical training
Collaborative multi-user XR for remote clinical consultation
AI-based rendering and scene understanding for XR

Foundation and self-supervised models for medical 3D vision

Self-supervised pretraining on 3D medical volumes
Universal anatomical segmentation with foundation models
Parameter-efficient fine-tuning for 3D clinical tasks with minimal labeled data
Continual and federated pretraining of 3D foundation models

Learning from sparse, noisy, or heterogeneous medical data

Semi-supervised and few-shot 3D segmentation with foundation model priors
Federated learning for multi-view 3D imaging
Uncertainty quantification for clinical deployment of 3D models
Label-efficient learning from noisy and partially annotated 3D medical data

CFP

Call for Papers

Submission Guidelines

All papers should be submitted at: Link
Papers must be prepared according to the ECCV Submission Guidelines. All papers will be reviewed by at least two reviewers with double-blind peer-review policy. Manuscripts must be submitted as PDF documents following the ECCV 2026 Submission Template.
Submissions are limited to 14 pages. Additional pages containing only cited references are allowed. Supplemental materials are also allowed, in PDF format.
Accepted papers will be published as part of the ECCV 2026 proceedings.
We also welcome papers previously submitted to other venues, but they will not be included in the conference proceedings.
Authors are further urged to consult ECCV 2026's ethics guidelines, recommended best practices, and FAQs.

Key Dates

Submission deadline July 10, 2026

Decision to authors August 6, 2026

Camera-ready deadline August 15, 2026

Workshop date September 9, 2026 AM

All deadlines at 23:59 Anywhere on Earth (AoE).

Speakers

Invited Speakers

Federico Bolelli

University of Modena and Reggio Emilia, Italy

Tenure-Track Assistant Professor at the University of Modena and Reggio Emilia, where he is part of the AImagelab research group. He earned his B.Sc. and M.Sc. degrees (cum laude) in Computer Engineering and completed his Ph.D. in ICT at the same university.

His research spans image processing, algorithm optimization, and medical imaging, including optimization of binary image processing on CPU/GPU, skin lesion segmentation for melanoma detection, CBCT maxillofacial segmentation, and whole-slide image analysis. He contributed to the H2020 DeepHealth project (co-leading the European Computer Vision Library, ECVL) and has been involved in the H2020 DECIDER project since 2022. Federico chairs the IAPR Technical Committee (TC22) on Reproducible Research and is a member of IEEE, MICCAI, and CVPL. He serves as Associate Editor for Pattern Recognition and Simulation & Game.

Amine Ouasfi

INRIA, France

Computer Vision PhD Student at INRIA, France, working with Prof. Adnane Boukhayma and Prof. Eric Marchand. His research focuses on deep learning for 3D reconstruction (creating virtual twins) and 3D generative AI.

He has worked on improving generalizable implicit reconstruction models and implicit representation learning from sparse inputs (point clouds, multi-view images). He is currently exploring how to improve the controllability of video generation for 3D-oriented tasks.

Organizers