BMVC2024 Workshop

DIFA: Deep Learning-based Image Fusion and Its Applications

27th November, 2024, Glasgow, UK

1University of Exeter 2University of Sheffield 3Queen's University Belfast 4Imperial College London

Introduction

Image fusion has been a subject of study for over 30 years. The field experienced a significant milestone in around 2017 with the introduction of deep learning techniques. Since then, deep learning-based image fusion has attracted significant attention, leading to substantial progress in algorithms, datasets, and benchmarks. Furthermore, image fusion has demonstrated its utility across a wide range of applications, including object tracking, object detection, medical image processing, robotics, autonomous driving, scene segmentation, pedestrian and cyclist detection, salient object detection, power facility inspection, surveillance, face recognition, crowd counting, vital sign measurement, motion estimation and crack detection in civil infrastructure. This workshop provides a opportunity to gather researchers from the image fusion community, allowing them to review the current technological trends in image fusion and its applications, as well as discuss its future developments. This workshop also provides an opportunity for researchers in other fields to find out how they can benefit from image fusion technologies.

Call for papers

The workshop will cover (but is not limited to) the following topics:

1. Different image fusion tasks
  • Visible and infrared image fusion, multi-focus image fusion, multi-exposure image fusion, medical image fusion, remote sensing image fusion, multimodal image fusion, general image fusion, and other types of image fusion.
2. Deep learning methods for image fusion
  • CNN-based methods, GAN-based methods, autoencoder-based methods, transformer-based methods, diffusion model-based methods, application-driven image fusion methods, image registration methods for image fusion, etc.
3. Dataset and performance evaluation
  • Image fusion datasets, image fusion evaluation metrics, image fusion evaluation methods, image fusion benchmarks
4. Image fusion applications
  • Object tracking, object detection, scene segmentation, robotics, etc.
5. Fusion of images with other modalities
  • Image + tactile data, image + Lidar data, etc.

Download CFP

Important dates

  • Submission deadline: August 6th 2024, 23:59 (UK time)
  • Submission deadline: August 14th 2024, 23:59 (UK time)
  • Notification of acceptance: August 16th, 2024
  • Notification of acceptance: August 24th, 2024
  • Notification of acceptance: August 27th, 2024
  • Camera-ready submission: September 16th, 2024
  • Camera-ready submission: September 26th, 2024

Paper submission

Accepted Papers

  • IRFusionFormer: Enhancing Pavement Crack Segmentation with RGB-T Fusion and Topological-Based Loss
  • Y-Net: Fusing fMRI and Natural Scenes to Generate Neuro-Interpretable Heat Maps
  • GlowNet: A Lightweight Attention based Self-Guided Deep Neural Network for Low-Light Image Enhancement
  • FourierDiff: Image Denoising Using Improved Denoising Diffusion Probabilistic Models via Fast Fourier Convolution

Tentative Program (subject to change)

  • 14:00 - 14:10 Opening Remarks
  • 14:10 - 15:30 Keynotes
  • 15:30 - 15:40 Break
  • 15:40 - 15:55 Oral presentation: Paper 1
  • 15:55 - 16:10 Oral presentation: Paper 2
  • 16:10 - 16:25 Oral presentation: Paper 3
  • 16:25 - 16:40 Oral presentation: Paper 4
  • 16:40: -17:00 Break
  • 17:00 - 17:05 Best paper award announcement
  • 17:05 - 17:10 Closing Remarks

Registration and Attendance

Registration

Please complete your registration on the BMVC2024 website: https://bmva.charitysuite.com/events/zz5rrcqk. You can choose whole BMVC conference registration (Early bird registration is £550, ends in 30th September), or One-day Workshop only Registration (£100).

Attendance

Our workshop will be run in hybrid mode. After you complete your registration, please send us an email with proof of registration. We will send you the online link before the workshop.

Keynote Speakers

Bartek Papiez

Bartek Papiez

Associate Professor

University of Oxford

Hui Wang

Hui Wang

Professor

Queen's University Belfast

Organisers

Xingchen Zhang

Xingchen Zhang

Senior Lecturer

University of Exeter

Zhixiang Chen

Zhixiang Chen

Lecturer

University of Sheffield

Shuyan Li

Shuyan Li

Lecturer

Queen's University Belfast

Yiannis Demiris

Yiannis Demiris

Professor

Imperial College London

Contact

  • To contact the organizers please use x.zhang12@exeter.ac.uk
University of Exeter Logo University of Sheffield Logo Queen's University Belfast Logo Imperial College London Logo