NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results

2026-04-12

AI Summary

This work addresses the challenge of low-quality short-form user-generated content (S-UGC) videos in real-world scenarios, where complex degradations hinder effective restoration. To bridge the gap in existing research, the authors introduce KwaiVIR, the first generative video restoration benchmark specifically designed for real S-UGC videos, integrating both synthetically generated and real degraded data. The benchmark employs a dual-track evaluation framework combining subjective user studies with objective quality metrics. Leveraging this benchmark, a large-scale challenge attracted 95 participating teams, with 12 submitting valid solutions that demonstrated significant advances in video quality restoration, thereby accelerating the development and practical application of generative models for real-world video enhancement.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.

Problem

• Short-form UGC video
• Video restoration
• In the wild
• Real-world degradations
• Generative models

Innovation

• generative video restoration
• short-form UGC
• KwaiVIR benchmark
• in-the-wild degradation
• subjective-objective evaluation