The workshop focuses on unifying new streaming technologies, computer graphics, and computer vision, from the modern deep learning point of view. Streaming is a massive industry where hundreds of millions of users demand everyday high-quality content on different platforms. Computer vision and deep learning have emerged as revolutionary forces for rendering content, image and video compression, enhancement, and quality assessment. From neural codecs for efficient compression to deep learning-based video enhancement, these advanced techniques are setting new standards for streaming quality and efficiency. Moreover, novel neural representations also pose new challenges and opportunities in rendering streamable content and allowing to redefine computer graphics pipelines and visual content.

As part of the workshop, we organized several challenges on efficient super-resolution, quality assessment, eye tracking and more. Please check the workshop website for more information.

We invite researchers and engineers from academia and industry to join us to learn more about the future of streaming.

Speakers

The workshop counts with the following invited speakers from academia and industry:

  • Prof. Alan Bovik (University of Texas at Austin): Video Quality Assessment
  • Dr. Lucas Theis (Google DeepMind): Neural Compression
  • Dr. Ryan Lei (Meta): Machine Learning for Video Compression
  • Dr. Kelvin Chan (Google DeepMind): Video Super-Resolution
  • Dr. Christos Bampis (Netflix): Deep Video Pre-processing

Stay tuned! We plan to host more interesting talks on video generation.

About CVPR

The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) is the premier annual computer vision event comprising the main conference and several co-located workshops and short courses. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers.

When and Where

The workshop will be held on Monday June 17th, from 9:00am to 5:30pm PT.

Seattle Convention Center, Arch 3A.

Organizers and Sponsors

This workshop is a collaboration project between different academia and industry labs.

Marcos V. Conde (University of Würzburg & Sony PlayStation, VCG), Radu Timofte (University of Würzburg), Ioannis Katsavounidis (Meta), Ryan Lei (Meta), Daniel Motilla (Sony PlayStation, VCG), Christos Bampis (Netflix),  Rakesh Ranjan (Meta Reality Labs).Website: AIS: Vision, Graphics and AI for Streaming @ CVPR 2024 Workshop (ai4streaming-workshop.github.io)