mlsanityData to 14 Oct 2026

NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results

arXiv 2506.02875 ↗First posted 3 Jun 2025cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. This challenge is to address a major challenge in the field of video and talking head processing. The challenge is divided into three tracks, including user generated video, AI generated video and talking head. The user-generated video track uses the FineVD-GC, which contains 6,284 user generated videos. The user-generated video track has a total of 125 registered participants. A total of 242 submissions are received in the development phase, and 136 submissions are received in the test phase. Finally, 5 participating teams submitted their models and fact sheets. The AI generated video track uses the Q-Eval-Video, which contains 34,029 AI-Generated Videos (AIGVs) generated by 11 popular Text-to-Video (T2V) models. A total of 133 participants have registered in this track. A total of 396 submissions are received in the development phase, and 226 submissions are received in the test phase. Finally, 6 participating teams submitted their models and fact sheets. The talking head track uses the THQA-NTIRE, which contains 12,247 2D and 3D talking heads. A total of 89 participants have registered in this track. A total of 225 submissions are received in the development phase, and 118 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 40 of its 48 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

40 of 48 references.

References · 40

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  2. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  3. 2020A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wildcited by 672
  4. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 546
  5. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  6. 2023EvalCrafter: Benchmarking and Evaluating Large Video Generation Modelscited by 340
  7. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  8. 2021Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motioncited by 149
  9. 2022A Deep Learning based No-reference Quality Assessment Model for UGC Videoscited by 129
  10. 2023FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generationcited by 122
  11. 2022VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wildcited by 106
  12. 2023Identity-Preserving Talking Face Generation with Landmark and Appearance Priorscited by 98
28 more
  1. 2021HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swappingcited by 92
  2. 2019MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targetscited by 90
  3. 2023DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Videocited by 74
  4. 2023Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approachcited by 45
  5. 2024NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Resultscited by 40
  6. 2024Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMscited by 39
  7. 2025Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Contentcited by 32
  8. 2020Mesh Guided One-shot Face Reenactment using Graph Convolutional Networkscited by 30
  9. 2024NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Resultscited by 29
  10. 2024FineVQ: Fine-Grained User Generated Content Video Quality Assessmentcited by 28
  11. 2022Finding Directions in GAN's Latent Space for Neural Face Reenactmentcited by 27
  12. 2023Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluationcited by 27
  13. 2024Quality Assessment in the Era of Large Models: A Surveycited by 26
  14. 2025NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Resultscited by 25
  15. 2023Measuring the Quality of Text-to-Video Model Outputs: Metrics and Datasetcited by 23
  16. 2023Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Modelscited by 22
  17. 2023StableVQA: A Deep No-Reference Quality Assessment Model for Video Stabilitycited by 15
  18. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  19. 2023Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancementcited by 12
  20. 2025NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Resultscited by 12
  21. 2024MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysiscited by 11
  22. 2025NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Resultscited by 9
  23. 2025NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolutioncited by 9
  24. 2025NTIRE 2025 challenge on Text to Image Generation Model Quality Assessmentcited by 8
  25. 2023An Implementation of Multimodal Fusion System for Intelligent Digital Human Generationcited by 6
  26. 2024Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidancecited by 6
  27. 20243DGCQA: A Quality Assessment Database for 3D AI-Generated Contentscited by 6
  28. 2024ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videoscited by 2

Built on by

Cited by year

Citing papers per year: 2025: 6.

6 papers.

  1. 2025EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humanscited by 4
  2. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  3. 2025Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Modelcited by 2
  4. 2025NTIRE 2025 Image Shadow Removal Challenge Reportcited by 1
  5. 2025Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Headscited by 1
  6. 2025NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Resultscited by 1