Skip to yearly menu bar Skip to main content


Poster

VBench: Comprehensive Benchmark Suite for Video Generative Models

Ziqi Huang · Yinan He · Jiashuo Yu · Fan Zhang · Chenyang Si · Yuming Jiang · Yuanhan Zhang · Tianxing Wu · Jin Qingyang · Nattapol Chanpaisit · Yaohui Wang · Xinyuan Chen · Limin Wang · Dahua Lin · Yu Qiao · Ziwei Liu

Arch 4A-E Poster #219
Highlight Highlight
[ ] [ Project Page ] [ Paper PDF ]
[ Poster
Fri 21 Jun 10:30 a.m. PDT — noon PDT

Abstract:

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide insights to inform future developments of video generation. To this end, we present VBench, a comprehensive benchmark suite that dissects "video generation quality" into specific, hierarchical, and disentangled dimensions, each with tailored prompts and evaluation methods. VBench has three appealing properties: 1) Comprehensive Dimensions: VBench comprises 16 dimensions in video generation (e.g., subject identity inconsistency, motion smoothness, temporal flickering, and spatial relationship, etc). The evaluation metrics with fine-grained levels reveal individual models' strengths and weaknesses. 2) Human Alignment: We also provide a dataset of human preference annotations to validate our benchmarks' alignment with human perception, for each evaluation dimension respectively. 3) Valuable Insights: We look into current models' ability across various evaluation dimensions, and various content types. We also investigate the gaps between video and image generation models. We will open-source VBench, including all prompts, evaluation methods, generated videos, and human preference annotations, and also include more video generation models in VBench to drive forward the field of video generation.

Chat is not available.