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.

CHALLENGE TRACKS

There are two challenge tracks. In the low bit-rate track, images need to be compressed to below 0.15 bits per pixel (bpp). This is the same task as in previous years, which allows us to measure progress over the years. As a first step towards video compression, this year also includes a P-frame track. Here, video P-frames need to be predicted from a previous frame.

Low-rate compression

For the low bit-rate track (which is similar to the one we ran at CLIC 2018), contestants will be asked to compress the entire dataset to 0.15 bpp or smaller. The winners of the competition will be chosen based human perceptual rating task and will be asked to give a short talk at the CLIC workshop. PSNR and MS-SSIM will be evaluated but not considered for prizes. We will provide last year’s professional and mobile datasets (all splits) as the training data for this challenge track. A new test set will be generated for this year and released during the test phase.

P-frame compression

The P-frame challenge will require entrants to compress a video frame conditioned on the previous image frame. Instead of splitting the dataset into training and test sets, in this track the entire dataset is released before the test phase. To discourage overfitting, the model size is added to the compressed dataset size and the sum cannot exceed a target bit-rate. That is, participants should try to minimize both the dataset size and the model size. The winner will be determined based on MS-SSIM.

REGULAR PAPERS

We will have a short (4 pages) regular paper track, which allows participants to share research ideas related to image compression. In addition to the paper, we will host a poster session during which authors will be able to discuss their work in more detail.

We encourage exploratory research which shows promising results in:

CHALLENGE PAPERS

The challenge task participants are asked to submit a short paper (up to 4 pages) detailing the algorithms which they submitted as part of the challenge.

SUBMISSION (TBA)

IMPORTANT DATES

SPEAKERS

ORGANIZERS

SPONSORS (TBU):