<div dir="ltr">
<div dir="ltr"><div><span>Apologies for cross-posting<br>*******************************<br></span><br><span>CALL FOR PARTICIPANTS & PAPERS<br><br></span>CLIC: 3rd Workshop and Challenge on Learned Image Compression <span>2020</span>
<br>in conjunction with <span><span>CVPR</span></span> <span>2020</span>, June 14, Seattle, USA.<br>
<br>Website: <a href="http://www.compression.cc/" target="_blank">http://www.compression.cc/</a></div><div><br></div><div>
<br></div><div>MOTIVATION<br></div><div><div dir="ltr"><div>
<br>
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.
<br>
</div><div><br></div><div><br>
CHALLENGE TRACKS
<br>
<br>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.
<br>
<br>Low-rate compression
<br>
<br>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.
<br>
<br>
<br>P-frame compression
<br>
<br>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.
<br>
<br>
<br>REGULAR PAPERS<br>
<br>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.
<br></div><div><br></div><div>We encourage exploratory research which shows promising results in:
<br><div style="margin-left:40px">● Lossy image compression
<br>● Quantization (learning to quantize; dealing with quantization in optimization)
<br>● Entropy minimization
<br>● Image super-resolution for compression
<br>● Deblurring
<br>● Compression artifact removal
<br>● Inpainting (and compression by inpainting)
<br>● Generative adversarial networks
<br>● Perceptual metrics optimization and their applications to compression
<br>And, in particular, how these topics can improve image compression.
<br>
</div></div><div><br>
<br>
CHALLENGE PAPERS
<br>
<br>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.
<br>
</div><div><br></div><div><br>
SUBMISSION (TBA)
<br>
</div><div><br></div><div><br>
IMPORTANT DATES
<br>
<br><div style="margin-left:40px">
November 22th 2019 Development phase & announcement. The training part of the dataset released.
<br>January 7th, 2020 The validation part of the dataset released, online validation server is made available.
<br>March 13th, 2020 Final decoders for the challenge are expected to be submitted.
<br>March 16th, 2020 Test set is released for contestants to compress.
<br>March 20th, 2020 Encoded test set submission deadline. The competition is closed at this point.
<br>March 23th, 2020 Paper and Factsheet submission deadline.per and Factsheet submission deadline.
<br>April 6th, 2020 Paper decision notification.
<br>Mid April, 2020 Camera ready deadline for CVPR
<br>Mid May, 2020 End of human evaluation on both challenges. Results will be released online before the workshop.
<br></div>
</div><div><br></div><div><br>SPEAKERS
<br>
<br><div style="margin-left:40px">
Nils Thuerey, Technical University of Munich, Germany
<br>Yochai Blau, Technion, Israel
<br>Tom Bird, UCL, London
<br></div>
</div><div><br></div><div><br>ORGANIZERS
<br>
<br><div style="margin-left:40px">
George Toderici (Google)
<br>Wenzhe Shi (Twitter)
<br>Radu Timofte (ETH Zurich)
<br>Lucas Theis (Twitter)
<br>Johannes Ballé (Google)
<br>Eirikur Agustsson (ETH Zurich / Google)
<br>Nick Johnston (Google)
<br>Fabian Mentzer (ETH Zurich) <br></div><br>SPONSORS (TBU):<br>
<br><div style="margin-left:40px"></div><div style="margin-left:40px"> </div><div style="margin-left:40px">Google
<br> Twitter <br></div><div style="margin-left:40px">CVL / ETH Zurich</div><div style="margin-left:40px">
Huawei<br></div><div style="margin-left:40px">Disney Research</div><div style="margin-left:40px">
MediaTek</div>
<div><br>Website: <a href="http://www.compression.cc/" target="_blank">http://www.compression.cc/</a></div></div></div></div></div>
</div>