Introduction

CLIC 2025, the 7th Challenge on Learned Image Compression, aims to advance the field of image and video compression using machine learning and computer vision. It is also an opportunity to evaluate and compare end-to-end trained approaches against classical approaches. We encourage the development of novel encoder/decoder architectures, novel ways to control information flow between the encoder and the decoder, new perceptual losses, and new ways to learn quantized representations.

Location

CLIC submissions and winners will be honored in a mini-workshop on 8 December, 2025, as part of the Picture Coding Symposium. Registration for the symposium is required to attend. There will be a half-day program, including talks given by the winners of the challenge, and a poster session, where each participant can present their method. Prizes will be awarded during the PCS social event.

Participation

The challenge has a validation phase and a test phase. Submissions will be ranked on this website during the validation phase. The actual winners will be determined during the test phase. For detailed instructions, refer to the tasks page.

To qualify, each participant team must:

• submit at least one decoder during the validation phase,
• submit compressed files during the test phase, matching a previously submitted decoder, and
• submit an accompanying whitepaper through OpenReview.

Technical novelty is not a requirement for the whitepapers. However, they must include a self-contained description of the method, detailed enough to reproduce the results. Accepted papers will be linked on the papers page.

Challenge participants are specifically encouraged to submit papers about their method to the PCS submission site (CMT). These papers will undergo the regular PCS submission process. Accepted conference papers will be published on IEEE Xplore.