[visionlist] [Challenge & CfP] AINIME at WACV27 Anime Restoration Challenge

[Georgia Fargetta]

Dear colleagues,

We are happy to announce the start of the AINIME Anime Restoration Challenge @ WACV 2027, the flagship challenge of the AINIME workshop (AI for Animation), held at WACV 2027 (January 4–5, 2027).
Workshop and Challenge page: https://mv-lab.github.io/ainime/

Enhance the perceptual quality of anime video clips from Re-Anime600, a curated benchmark of 600 clips with high native quality, while preserving the content, style and temporal consistency of the original animation. The data is split into 350 train clips (public after signing the data agreement), 100 validation clips and 150 test clips (hidden).

Register your team: https://docs.google.com/forms/d/e/1FAIpQLSfnYjhFO2Me3EcyD2xPB0Y_fDNgX97gcSpjFrPR17UTIuKwjw/viewform
- Train data: https://huggingface.co/datasets/ainime-challenge/re-anime600-train. Access requires signing the AINIME Challenge Data Agreement.
- Submission example: https://github.com/Zero9667/ainime-wacv2027-submission-example

Important dates
- Oct 2, 2026: challenge opens, train data available
- Oct 2 – Oct 20: validation phase
- Oct 20 (AoE): deadline for challenge paper submission
- Oct 21 – Oct 25: test phase
- Oct 28: results announced

Prizes
Special issue publication: Top teams will be invited to publish their work in a special issue of (Q1 Computer Science). Invited papers will go through the regular peer-review process of the journal.

Workshop registration: the participation fee for the AINIME workshop at WACV 2027 will be covered for one representative per winning team.

Challenge report and papers
Participating teams are invited to describe their method in a paper: regular papers, 5–8 pages (excluding references), double-blind review via OpenReview. The track is archival: accepted papers appear in the WACV 2027 workshop proceedings and in IEEE Xplore. The paper deadline is Oct 20 (AoE).

Organizers
Marcos V. Conde, Georgia Fargetta, Zhihao Cui,
Jeonghun Baek, Rosario Licciardello, Jin Yeying (Tencent), Julian Tanke (Sony AI).

Contact
georgia.fargetta at unict.it, 1000069335 at studium.unict.it

We look forward to your participation, and please feel free to forward this call to anyone who might be interested.

Best regards,
The AINIME Challenge Organizers
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20261002/3a3f5530/attachment.htm>