Research map / Video / Video generation
VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation
Longteng Jiang, DanDan Zheng, Qianqian Qiao, Heng Huang, Huaye Wang, Yihang Bo, Bao Peng, Jingdong Chen, Jun Zhou, Xin Jin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| compare Sora2 with Wan2.1 on aesthetics | Sora2 · VGA-Bench | aesthetic score: 0.46 -> 0.50 | Improved |
| compare Sora2 with CogVideoX on tag classification | Sora2 · VGA-Bench | aesthetic tag classification accuracy: 0.39 -> 0.18 | Hurt |
| compare Show-1 with SVD on generation level | Show-1 · VGA-Bench | generation level: 0.55 -> 0.28 | Hurt |
| compare Hunyuan with Mochi on aesthetics | Hunyuan · VGA-Bench | aesthetic score: 0.21 -> 0.45 | Improved |
| rank by model scores versus human ranking, aesthetic versus generation | VGA-Bench evaluators · User study (40 questionnaires) | Recall@1: 0.10 -> 0.50 | Mixed |
| fine-tune VAQA-Net on generated videos for overall aesthetics versus lighting | VAQA-Net · VAQA-Net evaluation (400 generated videos) | 5-class accuracy (%): 76.9 -> 69.5 | Mixed |
Closest papers by meaning
- VBench: Comprehensive Benchmark Suite for Video Generative Models (CVPR 2024 · similarity 0.91)
- Video-Bench: Human-Aligned Video Generation Benchmark (CVPR 2025 · similarity 0.91)
- VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment (AAAI 2025 · similarity 0.89)
- VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations (NeurIPS 2025 · similarity 0.89)
- EvalCrafter: Benchmarking and Evaluating Large Video Generation Models (CVPR 2024 · similarity 0.89)
- Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs (CVPR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
