NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results

2025-05-05

AI Summary

Real-world user-generated content (UGC) videos suffer from multiple degradations—including noise, blur, color fading, and compression artifacts—posing significant challenges for no-reference video enhancement. To address this, we introduce UGC-Video, the first large-scale, multi-degradation, no-reference benchmark comprising 150短视频 clips tailored for short-video platforms, accompanied by a large-scale no-reference enhancement challenge. We innovatively employ over 8,000 crowd-sourced subjective evaluations to establish a perception-driven assessment framework independent of PSNR/SSIM. Methodologically, we propose an end-to-end spatiotemporal joint modeling framework integrating degradation-aware feature extraction and perceptual consistency loss. The challenge attracted participation from 25+ teams, with seven successfully validating their methods via source-code reproduction. We fully open-source all enhanced results, subjective scores, and evaluation protocols—constituting, to date, the largest publicly available no-reference UGC video enhancement benchmark.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This paper presents an overview of the NTIRE 2025 Challenge on UGC Video Enhancement. The challenge constructed a set of 150 user-generated content videos without reference ground truth, which suffer from real-world degradations such as noise, blur, faded colors, compression artifacts, etc. The goal of the participants was to develop an algorithm capable of improving the visual quality of such videos. Given the widespread use of UGC on short-form video platforms, this task holds substantial practical importance. The evaluation was based on subjective quality assessment in crowdsourcing, obtaining votes from over 8000 assessors. The challenge attracted more than 25 teams submitting solutions, 7 of which passed the final phase with source code verification. The outcomes may provide insights into the state-of-the-art in UGC video enhancement and highlight emerging trends and effective strategies in this evolving research area. All data, including the processed videos and subjective comparison votes and scores, is made publicly available at https://github.com/msu-video-group/NTIRE25_UGC_Video_Enhancement.

Problem

• Enhancing visual quality of user-generated videos
• Addressing real-world degradations like noise and blur
• Developing algorithms for UGC video improvement

Innovation

• UGC video enhancement without ground truth
• Subjective quality assessment via crowdsourcing
• Public dataset with processed videos and scores