Arts · OECD FoS 6.4 · China MoE 1354 戏剧与影视
Film & animation
影视与动画
L2Local breakthroughs ↑ Rising Score 1.60 · Last reviewed 2026-10-22 · Next review 2027-01-19
BIGGEST BREAKTHROUGH 2024-02-15 AI leapField · major
OpenAI unveils text-to-video model Sora ↗
First minute-long high-fidelity video model
Why this level
Text-to-video (Sora from 2024) has entered production; the 99th Oscars rules (May 2026) say generative AI use does not disqualify a film, but acting and writing awards require human work.
S = 0.30·method + 0.35·discovery + 0.25·adoption + 0.10·education (education scores 0 when there is no evidence; if empty, the other weights are renormalised)
Sources
Composite 1.5–2.49: at least one peer-reviewed/officially verified AI-key result, or one dimension at 3; routine workflow largely unchanged. All levels →
Research directions
Text-to-videoVirtual production & VFXDubbing & digital humans
Papers
- Movie Gen: A Cast of Media Foundation Models
Joint video and audio generation
2024-10-17 · arXiv
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
Open video generation becomes usable
2023-11-25 · arXiv
- Rethinking Video Autoencoders for Interactive World Models
Rethinks video autoencoders for interactive world models, trading compression against action latency.
2026-10-21 · arXiv · Adrien Ramanana Rahary, Yutong Bai, Nicolas Dufour, Patrick Pérez
- CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion
A causal alignment framework that reduces long-horizon camera ego-motion drift in video generation models.
2026-10-21 · arXiv · Kai Zhu, Yintianrun Zhang, Shuwei Jiang, Ruolin Zuo
- Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs
Co-generates video, replayable 3D motion for arbitrary rigs, and a registered camera.
2026-10-20 · arXiv · Noam Rotstein, Yoad Tewel, Chen Tessler, Haggai Maron
- AEON: Unifying Video and 3D World Models
Generates renderable 4D Gaussians from video latents, unifying video and 3D world models.
2026-10-20 · arXiv · Weiqi Zhang, Wenyuan Zhang, Yu-Shen Liu, Junsheng Zhou
- InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation
Procedural generation of open-ended photorealistic 3D worlds.
2026-10-19 · arXiv · Yi-Chuan Huang, Hao-Jen Chien, Zheng-Hui Huang, Yu-Lun Liu
- Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning
Multi-agent manga-to-animation via script and storyboard planning.
2026-10-19 · arXiv · Sheng-Wei Zhang, Hsi-An Chen, Yan-Ting Liou, Chih-Hsuan Chen
- Mise-en-Video: Fine-Grained 3D Control for Multi-Shot Video Generation
Fine-grained 3D control for consistent multi-shot video generation.
2026-10-19 · arXiv · Yingshuang Zou, Xiaoyu Shi, Yawen Luo, Ziang Li
- PVBench: Quantifying Physical Plausibility in Video Generation with Object-Level Physical Measurements
Measures physical plausibility of generated videos across 46 dimensions.
2026-10-19 · arXiv · Kaiwei Chen, Moran Li, Zhenye Gan, Yabiao Wang
- From arXiv, bioRxiv, medRxiv and OpenAlex (last ~30 days); summaries written by AIMap from the abstract.
- Learning the 4D World through Point Trajectory Forecasting 2026-10-20
- Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs 2026-10-20
- Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning 2026-10-19
- SpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration 2026-10-19
- Speculative Forcing for Efficient Autoregressive Video Generation 2026-10-15
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation 2026-10-14
- All related papers in the archive →
Milestones 7· 1 leaps
Big glowing nodes are leaps: AI leap cool · Field leap warm · double ring = both
-
Industry
Netflix says generative AI has been used on about 300 titles; director Kang Yoon-sung cites 30–40% budget savingsAI: generative AI now in mainstream streaming production. Field: Netflix’s first adoption figure (~300 titles); savings are a director’s estimate
VarietyVendor claim -
Industry
Fully AI-generated feature “Gods Don’t Give Gifts” releases trailer; theatrical release and Oscar bid plannedAI feature enters theatrical distribution (not yet released)
Variety -
Deployment
Netflix uses generative AI for final on-screen VFX for the first time (El Eternauta)First generative-AI final footage in a major streamer original
Reuters -
System
Movie Gen: Meta’s media foundation models with synced audioJoint video and audio generation
arXivPreprint -
SystemAI leap
OpenAI unveils text-to-video model SoraFirst minute-long high-fidelity video model
OpenAI -
System
Stable Video Diffusion: open video generation modelOpen video generation becomes usable
arXivPreprint
No milestones match this filter.
More papers & repos 2
| Type | Title | Date |
|---|---|---|
| Paper | Movie Gen: A Cast of Media Foundation Models Preprint | 2024-10-17 |
| Paper | Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets Preprint | 2023-11-25 |
Latest news 12
- 奥斯卡大师加持，「电影精神」怎么造就AI剧场？雷峰网zh
- AI短剧里的“彩票工厂”不再赚钱钛媒体zh
- Why Film Studios Are Trading Sound Stages for Data CentersNo Film Schoolen
- ‘Artificial’ is not the AI film we deserveTransformeren
- What Mattered to Hollywood at This Year’s Iberseries & Platino IndustriaHollywood Reporteren