AI Paper Atlas

Research map / Video / Video generation

HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

Yihao Meng, Hao Ouyang, Yue Yu, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Hanlin Wang, Shuailei Ma, Yixuan Li, Cheng Chen, Yanhong Zeng, Xing Zhu and 2 more

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 41 citations (OpenAlex)

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 changedWhereMeasuredEffect
add window cross-attention (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkTransition Control (SCA): 0.6266 -> 0.9736Improved
add window cross-attention (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkSemantic Consistency: 0.1562 -> 0.1739Improved
add window cross-attention (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkInter-shot Consistency: 0.7009 -> 0.7225Improved
add window cross-attention (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkAesthetic Quality: 0.5755 -> 0.5693No clear effect
add inter-shot summary tokens (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkInter-shot Consistency: 0.6761 -> 0.7225Improved
add inter-shot summary tokens (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkSemantic Consistency: 0.1642 -> 0.1739Improved
add inter-shot summary tokens (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkTransition Control (SCA): 0.9675 -> 0.9736Improved
use sparse inter-shot attention instead of full attention (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkInter-shot Consistency: 0.7231 -> 0.7225No clear effect
use sparse inter-shot attention instead of full attention (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkTransition Control (SCA): 0.8923 -> 0.9736Improved
use sparse inter-shot attention instead of full attention (ablation)HoloCine (Wan2.2 5B) · Multi-shot ablation benchmarkSemantic Consistency: 0.1738 -> 0.1739No clear effect
holistic multi-shot fine-tuning of Wan2.2 14BHoloCine · Multi-shot benchmark (100 prompts)Transition Control (SCA): 0.4843 -> 0.9837Improved
holistic multi-shot fine-tuning of Wan2.2 14BHoloCine · Multi-shot benchmark (100 prompts)Inter-shot Consistency: 0.6772 -> 0.7509Improved

Later papers that compared with this method

1 later accepted paper reports HoloCine as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy