CLIC 2019 : CVPR 2019- Workshop and Challenge on Learned Image Compression
Call For Papers
CLIC: Workshop and Challenge on Learned Image Compression 2019
in conjunction with CVPR 2019
The domain of image compression has traditionally used approaches discussed in forums such as ICASSP, ICIP and other very specialized venues like PCS, DCC, and ITU/MPEG expert groups. This workshop and challenge will be the first computer-vision event to explicitly focus on these fields. Many techniques discussed at computer-vision meetings have relevance for lossy compression. For example, super-resolution and artifact removal can be viewed as special cases of the lossy compression problem where the encoder is fixed and only the decoder is trained. But also inpainting, colorization, optical flow, generative adversarial networks and other probabilistic models have been used as part of lossy compression pipelines. Lossy compression is therefore a potential topic that can benefit a lot from a large portion of the CVPR community.
Recent advances in machine learning have led to an increased interest in applying neural networks to the problem of compression. At CVPR 2017, for example, one of the oral presentations was discussing compression using recurrent convolutional networks. In order to foster more growth in this area, this workshop will not only try to encourage more development but also establish baselines, educate, and propose a common benchmark and protocol for evaluation. This is crucial, because without a benchmark, a common way to compare methods, it will be very difficult to measure progress.
We propose hosting an image-compression challenge which specifically targets methods which have been traditionally overlooked, with a focus on neural networks (but also welcomes traditional approaches). Such methods typically consist of an encoder subsystem, taking images and producing representations which are more easily compressed than the pixel representation (e.g., it could be a stack of convolutions, producing an integer feature map), which is then followed by an arithmetic coder. The arithmetic coder uses a probabilistic model of integer codes in order to generate a compressed bit stream. The compressed bit stream makes up the file to be stored or transmitted. In order to decompress this bit stream, two additional steps are needed: first, an arithmetic decoder, which has a shared probability model with the encoder. This reconstructs (losslessly) the integers produced by the encoder. The last step consists of another decoder producing a reconstruction of the original image.
In the computer vision community many authors will be familiar with a multitude of configurations which can act as either the encoder and the decoder, but probably few are familiar with the implementation of an arithmetic coder/decoder. As part of our challenge, we therefore will release a reference arithmetic coder/decoder in order to allow the researchers to focus on the parts of the system for which they are experts.
While having a compression algorithm is an interesting feat by itself, it does not mean much unless the results it produces compare well against other similar algorithms and established baselines on realistic benchmarks. In order to ensure realism, we have collected a set of images which represent a much more realistic view of the types of images which are widely available (unlike the well established benchmarks which rely on the images from the Kodak PhotoCD, having a resolution of 768x512, or Tecnick, which has images of around 1.44 megapixels). We will also provide the performance results from current state-of-the-art compression systems as baselines, like WebP and BPG.
We will be running two tracks on the the challenge: low-rate compression, to judged on the quality, and “transparent” compression, to be judged by the bit rate. For the low-rate compression track, there will be a bitrate threshold that must be met. For the transparent track, there will be several quality thresholds that must be met. In all cases, the submissions will be judged based on the aggregate results across the test set: the test set will be treated as if it were a single ‘target’, instead of (for example) evaluating bpp or PSNR on each image separately.
For the low-rate compression track, the requirement will be that the compression is to less than 0.15 bpp across the full test set. The maximum size of the sum of all files will be released with the test set. In addition, a decoder executable has to be submitted that can run in the provided Docker environment and is capable of decompressing the submitted files. We will impose reasonable limitations for compute and memory of the decoder executable. The submissions in this track that are at or below that bitrate threshold will then be evaluated for best PSNR, best MS-SSIM, and best MOS from human raters.
For the transparent compression track, the requirement will be that the compression quality is at least 40 dB (aggregated) PSNR; at least 0.993 (aggregated) MS-SSIM; and a reasonable quality level using the Butteraugli measure (final values will be announced later). The submissions in this track that are at or better than these quality thresholds will then be evaluated for lowest total bitrate.
We provide the same two training datasets as we did last year: Dataset P (“professional”) and Dataset M (“mobile”). The datasets are collected to be representative for images commonly used in the wild, containing around two thousand images. The challenge will allow participants to train neural networks or other methods on any amount of data (it should be possible to train on the data we provide, but we expect participants to have access to additional data, such as ImageNet).
Participants will need to submit a file for each test image.
Prizes will given to the winners of the challenges. This is possible thanks to the sponsors.
To ensure that the decoder is not optimized for the test set, we will require the teams to use one of the decoders submitted in the validation phase of the challenge.
Regular Paper Track
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:
● Lossy image compression
● Quantization (learning to quantize; dealing with quantization in optimization)
● Entropy minimization
● Image super-resolution for compression
● Compression artifact removal
● Inpainting (and compression by inpainting)
● Generative adversarial networks
● Perceptual metrics optimization and their applications to compression
And in particular, how these topics can improve image compression.
Challenge Paper Track
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.
All deadlines are 23:59:59 PST.
December 17th, 2018 Challenge announcement and the training part of the dataset released
January 8th, 2019 The validation part of the dataset released, online validation server is made available.
February 15th, 2019 The test set is released.
February 22th, 2019 The competition closes and participants are expected to have submitted their solutions along with the compressed versions of the test set.
February 28th, 2019 Results are released to the participants.
March 8th, 2019 Deadline for paper submission and factsheets.
March 22rd, 2019 Paper decision notification
March 30th, 2019 Camera ready deadline
Anne Aaron (Netflix)
Aaron Van Den Oord (Deepmind)
Jyrki Alakuijala (Google)
George Toderici (Google)
Michele Covell (Google)
Wenzhe Shi (Twitter)
Radu Timofte (ETH Zurich)
Lucas Theis (Twitter)
Johannes Ballé (Google)
Eirikur Agustsson (ETH Zurich)
Nick Johnston (Google)
Fabian Mentzer (ETH Zurich)