Generative Models in Image Processing (GMIP 2023)


Abstract: Generative models are powerful means of learning techniques that are used to learn the underlying distribution of features in datasets and produce representation or abstraction of observed phenomena in unsupervised manner. Generative models are successfully applied in major image processing areas and achieved tremendous performance with state-of-the-art results. Many of such high performance applications like text to image translation, face frontal view generation, new pose generation, 3D view generation, face aging estimation, increasing image resolution, photo inpainting, clothing translation and video prediction are deployed in real life scenarios where end-to-end paradigms are paramount important. Generative models have found numerous applications in image processing. Some of the prominent applications include: image synthesis where generative models are used to generate realistic images from random noise or latent vectors; image super-resolution where generative models are used to enhance the resolution and quality of low-resolution images; image inpainting where generative models are used to fill in missing or corrupted parts of an image; image style transfer where generative models are used to transfer the style of one image to another while preserving the content; image translation where generative models are used to translate images from one domain to another; image editing and manipulation where generative models can assist in image editing tasks and image compression where generative models can be employed for efficient image compression. These are just a few examples of how generative models are applied in image processing. The field is rapidly evolving, and new techniques are being developed, leading to exciting advancements in the generation, manipulation, and understanding of images.

The objective of this special session is to provide a vibrant platform for students, researchers and technologists to present and share their novel ideas and works in relevant areas. Contributions welcome on the topics of interest include but are not limited to

• Image editing and manipulation
• Text to image conversion
• Image to text conversion
• Image translation
• Human pose estimation
• Image super-resolution
• Image inpainting
• Clothing translation
• 2D to 3D image conversion
• Video prediction and generation
• Video generation from texts
• Biometrics
• Machine translation
• Speech synthesis
• Face frontalization
• Medical imaging
• Public healthcare
• Scene customization

The special session will be collocated with the 13th IEEE International Conference on Information Science and Technology (ICIST'23) to be held in Cairo, Egypt during December 8-14, 2023.

Deadlines:
Paper submission deadline: August 1, 2023
Notification of acceptance: September 1, 2023
Camera-ready copy and author registration: October 1, 2023

Paper submission link: https://easychair.org/account/signin?l=r8QxU4thQ1W0di6ZbGWEMr

Special Session Organizer:
Dr. Dakshina Ranjan Kisku
Associate Professor
National Institute of Technology Durgapur,
Durgapur – 713209, West Bengal, India
Email: drkisku@cse.nitdgp.ac.in