Introduction
VBench separates video quality into 16 dimensions, including subject consistency, motion, flicker and spatial relations, and checks metrics against human annotations.
View full image ↗Figure 1: VBench dimensions, prompts, evaluation methods and human annotations. Source: v1; the image version is distinct from the initial submission date.
Huang, Ziqi; He, Yinan; Yu, Jiashuo; Zhang, Fan; Si, Chenyang; Jiang, Yuming; Zhang, Yuanhan; Wu, Tianxing; Jin, Qingyang; Chanpaisit, Nattapol; Wang, Yaohui; Chen, Xinyuan; Wang, Limin; Lin, Dahua; Qiao, Yu; Liu, Ziwei · original paper / arXiv · Rights in the paper and depicted works remain with their holders. Research quotation does not establish an open licence; republication rights await independent review.
Source · VBench: Comprehensive Benchmark Suite for Video Generative Models ↗RESEARCH ACCOUNT
VBench separates video quality into 16 dimensions, including subject consistency, motion, flicker and spatial relations, and checks metrics against human annotations.
ANTI-AI ARCHIVE · Revised 2026-10-03
What the paper investigates
Each dimension receives its own prompts and evaluation method, exposing different model strengths and weaknesses. Human preference annotations test alignment with perception, while comparisons consider content types and the gap between still-image and video generation.
Section sources: VBench: Comprehensive Benchmark Suite for Video Generative Models
Its place in generative-art history
Editorial interpretation: viewing generated video cannot be reduced to the sharpness of one frame. Flicker, persistent subjects and organised motion make comparisons between technical demonstrations and moving-image production more precise.
Section sources: VBench: Comprehensive Benchmark Suite for Video Generative Models
Reading limits and versions
Agreement with annotations does not represent every audience, culture or film aesthetic. The benchmark was not rerun.
Section sources: VBench: Comprehensive Benchmark Suite for Video Generative Models
Sources for this account
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited.
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
VBench: compare methods, control or evaluation conditions with GenEval.
VBench: compare methods, control or evaluation conditions with Stable Video Diffusion.
VBench: compare methods, control or evaluation conditions with From images to video.
Dates & version record
Date displayed for this node: 2023-11-29 · Historical date recorded for the source: 2023-11-29
The timeline uses the initial arXiv submission, distinct from conference publication, model release and the archive addition on 3 October 2026. The account and image refer to v1; its date is recorded in the source history.
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
VBench: Comprehensive Benchmark Suite for Video Generative Models
https://arxiv.org/abs/2311.17982
Current cited URL
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited.
Provenance, translation & verification
Archive node #255 · Initial research-paper submission; methods, evaluation and production conditions
Research materials & supplement references · 1
Recent research papers: additions and reconciled sources since 2022 · Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited. · 023
Date as recorded: 2023-11-29
VBench: Comprehensive Benchmark Suite for Video Generative Models ↗
VBench: Comprehensive Benchmark Suite for Video Generative Models
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
Official material was read within the stated scope; see the source note for reading limits and outstanding checks.
Cite this node
ANTI-AI ARCHIVE. VBench: Comprehensive Benchmark Suite for Video Generative Models. Art-history node #255. https://salondesrefuses.cn/en/art-history/346
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.