NTIRE 2025 XGC AI-Generated Video Quality Assessment Challenge
The NTIRE 2025 XGC AI‑Generated Video Quality Assessment Challenge, hosted at the CVPR workshop, invites participants to build VQA models that predict mean opinion scores for 34,029 AI‑generated videos created from 4,689 prompts using 14 generation models, with training, validation, and test splits provided as JSON, and submissions evaluated by the average of PLCC and SROCC, while key dates run from February 5 to June 15 2025 and prize money up to $1,200 is offered.
The CVPR NTIRE 2025 workshop hosts the XGC Quality Assessment Challenge for AI‑Generated Video (AIGC). Participants must develop a VQA model that predicts perceptual quality scores (MOS) for videos generated from prompts.
The dataset contains 34,029 videos produced by 14 generation models (e.g., CogVideo, SVD) from 4,689 prompts. It is split 7:1:2 into training (23,820 videos with scores), validation (3,402 videos), and test (6,807 videos, no scores).
Training data is provided as JSON objects with fields: video, prompt, and gt_score. Validation and test sets include only video and prompt. Submissions must be JSON files containing video and predict_score, plus a README.
Evaluation metric: Score = (PLCC + SROCC) / 2.
Key dates: Feb 5 2025 – release of training/validation sets; Mar 14 2025 – release of test set; Mar 21 2025 – submission deadline; Apr 1 2025 – paper submission deadline; Jun 15 2025 – NTIRE workshop and award ceremony.
Prizes: 1st $1200, 2nd $1000, 3rd $800. Papers from top teams will be invited to the CVPR 2025 proceedings.
Organizers: Shanghai Jiao Tong University and Meituan. Contact: Wang Shushi ([email protected]). More information at https://cvlai.net/ntire/2025/ and https://codalab.lisn.upsaclay.fr/competitions/21485.
Meituan Technology Team
Over 10,000 engineers powering China’s leading lifestyle services e‑commerce platform. Supporting hundreds of millions of consumers, millions of merchants across 2,000+ industries. This is the public channel for the tech teams behind Meituan, Dianping, Meituan Waimai, Meituan Select, and related services.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.