<div dir="ltr">
<span>Apologies for multiple postings<br></span><div><span>***********************************</span></div><div><span><br></span></div><div><span></span></div><div><div><span><span>CALL</span></span> FOR <span><span>PAPERS</span></span> & <span><span>CALL</span></span> FOR PARTICIPANTS IN CHALLENGES</div><div><br></div><div>MAI 5<span>th <span>Mobile</span> <span>AI</span> <span>workshop and challenges on<span><span><br></span></span></span></span></div><div>Efficient LLMs, Efficient Stable Diffusion, Image/Video Super-Resolution, Efficient ViTs, Image Denoising, Bokeh Effect Rendering, Photo Enhancement, Learned Smartphone ISP
</div><div><span><span><span><span>validated on <span>mobile</span> hardware</span></span></span></span><br><span>In</span> conjunction with <span>CVPR</span> <span><span><span><span>2025</span></span></span></span>, 1?th of June, Nashville, US<br></div><div><br></div><div>
<div><div><div>Website:
https://<span>ai</span>-<a href="http://benchmark.com/workshops/mai/">benchmark.com/workshops/mai/</a><span>2025</span>/ <br></div><div>Contact: <a href="mailto:andrey@vision.ee.ethz.ch">andrey@vision.ee.ethz.ch</a><br></div><div><br></div><div>TOPICS</div><div><br></div><div style="margin-left:40px">
● Efficient deep learning models for <span>mobile</span> devices
<br>● Artifacts removal from <span>mobile</span> photos/videos
<br>● General smartphone photo/video enhancement
<br>● RAW camera image/video processing
<br>● Deep learning applications for <span>mobile</span> camera ISPs
<br>● Image/video super-resolution on low-power hardware
<br>● Portrait segmentation / bokeh effect rendering
<br>● Depth estimation w/o multiple cameras
<br>● Perceptual image manipulation on <span>mobile</span> devices
<br>● Activity recognition using smartphone sensors
<br>● Image/sensor based identity recognition
<br>● Fast image classification / object detection algorithms
<br>● NLP models optimized for <span>mobile</span> inference
<br>● Real-time semantic segmentation
<br>● Low-power machine learning inference
<br>● Machine learning and deep learning frameworks for <span>mobile</span> devices
<br>● <span>AI</span> performance evaluation / benchmarking of <span>mobile</span> and IoT hardware
<br>● Studies and applications of the above problems
<br></div>
<br>
</div></div><span><span><span><span><span><span><span><span><span><span><span></span></span></span></span></span></span></span></span></span></span></span>
</div>
<div><div>SUBMISSION<div><br></div><div>
<div>A <span><span>paper</span></span> submission has to be in English, in pdf format, and at most 8
pages (excluding references) in CVPR style. <br></div><div><a href="https://cvpr.thecvf.com/Conferences/2025/AuthorGuidelines">https://cvpr.thecvf.com/Conferences/2025/AuthorGuidelines</a></div><div>The review process is double blind. <br>
</div><div>Accepted and presented <span><span>papers</span></span> will be published after the conference
in the 2025 CVPR Workshops Proceedings.
<br>
<br>Author Kit: <a href="https://github.com/cvpr-org/author-kit/archive/refs/tags/CVPR2025-v3.1(latex).zip">https://github.com/cvpr-org/author-kit/archive/refs/tags/CVPR2025-v3.1(latex).zip</a></div><div>
</div><div>Submission site: <a href="https://cmt3.research.microsoft.com/MAI2025">https://cmt3.research.microsoft.com/MAI2025</a>
</div></div></div></div><div><br></div>
</div><div>WORKSHOP DATES</div><div><br></div><div>
<div><div style="margin-left:40px">
● <b><span>Regular Papers</span> submission deadline: March 10, <span><span><span>202</span></span></span><span><span>5<br></span></span></b></div><div style="margin-left:40px"><span><span></span></span></div><div style="margin-left:40px"><span><span><span></span></span></span></div><div style="margin-left:40px"><span><span><br></span></span></div>
<div><div>CHALLENGES (TBU)<br></div><div style="margin-left:40px"><br></div><div style="margin-left:40px">
<b>● Image Super-Resolution
<br>● Efficient LLMs
<br>● Efficient Stable Diffusion
<br>● Video Super-Resolution
<br>● Efficient ViTs for Mobile
<br>● Image Denoising
<br>● Bokeh Effect Rendering
<br>● RGB Photo Enhancement
<br>● Learned Smartphone ISP
</b> </div></div><div><br></div><div>To learn more about the challenges, to participate <span>in</span> the challenges,
<span>and</span> to access the data everybody is invited to check the <span><span><span>Mobile</span> <span>AI</span></span></span> <span>2025</span> web page:</div><div>
https://<span>ai</span>-<a href="http://benchmark.com/workshops/mai/">benchmark.com/workshops/mai/</a><span>2025</span>/
<div><div><br></div><div>For those interested in image and video restoration,
enhancement, manipulation, super-resolution, quality assessment without specific <span>mobile</span>
hardware constraints we refer to the <b>CVPR25 NTIRE Workshop and Challenges:</b></div>
<a href="https://cvlai.net/ntire/2025/">https://cvlai.net/ntire/2025/</a>
<div><br></div><div>
CHALLENGES DATES (TBU)<br><div>
<br><div style="margin-left:40px">● Release of train data: February 1, <span><span><span><span>2025</span></span></span></span><br>● <b>Competitions end: March 21, 2025<br></b></div><b><span><span><span></span></span></span></b><span><span><span></span></span></span><br></div><div>Website:
https://<span>ai</span>-<a href="http://benchmark.com/workshops/mai/">benchmark.com/workshops/mai/</a><span>2025</span>/</div></div></div></div></div></div>
</div>