Workshop and Challenge on Learned Image Compression


Nov 20th: The website of the 2020 edition of the workshop/challenge is online!

Nov 1: We have been approved for the Third Workshop and Challenge on Learned Image Compression at CVPR 2020. More information on the updated challenge and schedule will be available in the coming weeks.


Our workshop aims to gather publications which will advance the field of image and video compression using state of the art machine learning and computer vision techniques. Even with the long history of signal-processing oriented compression, taking new approaches to image processing have great potential, due to the proliferation of high-resolution cell-phone images and special hardware (e.g., GPUs and mobile AI accelerators). The potential in this area has already been demonstrated using recurrent neural networks, convolutional neural networks, and adversarial learning, many of these matching the best image-compression standards when measured on perceptual metrics. As such, we are interested in the various techniques associated with this class of methods. Broadly speaking, we would like to encourage the development of novel encoder/decoder architectures, novel ways to control information flow between the encoder and the decoder, novel optimization objectives for improved perceptual quality and learn how to quantize (or learn to quantize) better.

Workshop location

The workshop is held in conjunction with CVPR 2019, which will will take place June 14th - June 19th in Seattle, Washington (exact workshop day TBA). More information about the location and hotels can be found at


Lu Yu

Zhejiang University

Director of the Institute of Information and Communication Networks Engineering. Prof. Yu has been ISO/IEC JTC 1 / SC 29 / WG11 (MPEG) Video Chair since Jan. 2018. And she is Membership Chair of Visual Signal Processing and Communication TC and Elected Chair of Circuits and Systems Education and Outreach TC of IEE E Circuits and Systems Society, Steering Committee member of Picture Coding Symposim. She acted as Video Chair of the Audio and Video Coding Standardization Working Group of China (AVS) for 13 years, general chair of the 15th Workshop on Packet Video in 2016. Her research area is visual perception, visual perceptual quality assessment, visual signal representation and coding, multimedia intelligent processing, and related ASIC and SoC design, in which she is a principal investigator of a number of national R&D projects such as Natural Science Foundation of China, 863 Hi-tech Program and inventor of 80+ granted patents. She published more than 100 technical papers and contributed hundreds proposals to international and national standards in the past years.Read More

Nils Thuerey

Technical University of Munich

Nils Thuerey is an Associate-Professor at the Technical University of Munich (TUM). He focuses on deep-learning methods for physical data, with a special emphasis on fluids. Beyond latent-space simulation algorithms and learning with differentiable solvers, generative models have been a central theme of his work. Motivated by time-dependent problems from the physics area, Nils especially focuses on spatio-temporal data such as videos. Here, self-supervision in space as well as time has shown lots of promise, e.g., in form of the TecoGAN model, which can handle video super-resolution as well as unpaired video translation.Read More

Tom Bird


Tom is a machine learning researcher at UCL, London. Currently working towards his PhD, he has worked on probabilistic generative modelling and variational methods. He has made a novel contribution to lossless compression by being a part of the research team that developed BB-ANS, a way to convert latent variable ML models such as VAEs into practical lossless compression systems. Before beginning his PhD, he worked in quantitative finance and Fintech, after getting his BA & Master's in Maths from the University of Cambridge.Read More

Yochai Blau


Yochai recently completed his PhD thesis at the Technion, Israel, where he focused on fundamental tradeoffs in image compression and restoration. His contributions include theoretical research on the role of perceptual quality within modern image restoration and compression algorithms, as well as novel methodologi es for properly evaluating their performance. As part of this research, he co-organized the PIRM workshop and challenges at ECCV 2018, which promoted perceptual-quality-aware algorithms and evaluation schemes. Yochai is now working at Google on automated medicine through intelligent imaging.Read More

Workshop Schedule

Time Description
8 AM - 8.30 AM Poster Setup
8.30 AM - 8.45 AM Welcome and Schedule Overview
8.45 AM - 9.15 AM Invited Speaker
9.15 AM - 9.45 AM Invited Speaker
9.45 AM - 10 AM Short Break
10 AM - 10.30 AM Invited Speaker
10.30 AM - 11 AM Invited Speaker
11 AM - 12 PM Break
12 PM - 12.30 PM Dataset, Challenge, Rating Task
12.30 PM - 12.40 PM 3rd Lossy Track
12.40 PM - 12.50 PM 2nd Lossy Track
12.50 PM - 1 PM 1st Lossy Track
1 PM - 1.15 PM Break
1.15 PM - 1.25 PM 3rd P-frame Track
1.25 PM - 1.35 PM 2nd P-frame Track
1.35 PM - 1.45 PM 1st P-frame Track
1.45 PM - 2.00 PM Award Ceremony
2.00 PM - 2.30 PM Break
2.30 PM - 3.30 PM Poster Session
3.30 PM - 5.00 PM Break
5.00 PM - 5.45 PM Panel Discussion