The First Workshop on Journey to the Awards: Generative AI for Movie-Grade Video Production (J2A) at CVPR 2026 will explore how generative AI and multimodal LLMs can support the full film production pipeline. J2A emphasizes on studio-caliber cinematic video generation, and the integration of generative AI into the complete movie production pipeline, from ideation to post-production. We aim to bring together researchers and practitioners advancing generative tools that support studios and filmmakers in creating long-form, production-quality work with strong creative coherence. Topics of interest include movie-grade video generation, AI-assisted directing, automatic casting (such as AI-powered talent discovery and virtual auditions), storyboarding, cinematography, director's cut, editing, post-production, trailer generation, and more. Through these efforts, we envision generative AI advancing the creative industries and opening more pathways to cinematic storytelling.

The topics involved in the workshop include but are not limited to:

• Generative Video Modeling:
• Movie-grade video generation with diffusion models, autoregressive models, and hybrids.
• Long-form video generation with multi-scene temporal coherence and cinematic structure.
• Multimodal prompting techniques for narrative-driven generation.
• Large-scale datasets for cinematic video generation.
• Generative AI in Pre-Production:
• Script-to-video generation.
• AI-assisted storyboarding and shot planning.
• AI-assisted casting and character design.
• Multimodal LLMs for script writing and narrative coherence.
• Generative AI in Production:
• Virtual cinematography ("previz") and camera control.
• AI-driven directing and scene composition.
• Multi-agent collaboration for scene orchestration (coordinated arrangement and control of all visual, auditory, and narrative elements within a scene).
• Real-time feedback and (production-time) editing tools for movie creators.
• Generative AI in Post-Production:
• AI-assisted (semi-)automatic trailer generation.
• AI-powered editing and director's cuts.
• AI-assisted VFX generation, digital intermediate processing, and content enhancement.
• Evaluation and Quality Metrics:
• Benchmarking cinematic quality in AI-generated videos.
• Subjective vs. objective evaluation in creative media.
• Assessing narrative consistency and audience engagement.

Format: Submissions must use the CVPR 2026 Author Kit for Latex/Word Zip file and follow the CVPR 2026 author instructions and submission policies. Submissions need to be anonymized. A paper accepted to CVPR 2026 main conference can be resubmitted to our Extended Abstract track. A paper accepted by another venue can be resubmitted to our Extended Abstract track if allowed by that venue. Any submission to another CVPR 2026 Workshop cannot be resubmitted to J2A 2026. The workshop considers two submission tracks:

• Long Paper: submissions are limited to 8 pages excluding references, no appendix or supplementary;
• Extended Abstract: submissions are limited to 4 pages excluding references, no appendix or supplementary.

Only long papers will be included in the CVPR 2026 proceedings.

===

Submission Site: https://openreview.net/group?id=thecvf.com/CVPR/2026/Workshop/J2A

Submission Deadline: March 1, 2025 (AOE) March 6, 2026 (AOE)

Workshop Time and Location: June 4, 2026, 1PM-6PM, Room: Mile High 4CD

Please follow @felixudr on X for announcements and updates.

We are pleased to announce the accepted papers for the First Workshop on Journey to the Awards: Generative AI for Movie-Grade Video Production (J2A) at CVPR 2026. Congratulations to all authors!

Long Papers

• Title: TransAnimate: Taming Layer Diffusion to Generate RGBA Video
  Authors: Xuewei Chen, Zhimin Chen, Yiren Song
  [Poster #30]
• Title: CreativeVR: Diffusion-Prior-Guided Approach for Structure and Motion Restoration in Generative and Real Videos
  Authors: Tejas Panambur, Ishan Rajendrakumar Dave, Chongjian GE, Ersin Yumer, Xue Bai
  [Poster #30]

Short Papers

• Title: Seeking Universal Shot Language Understanding Solutions
  Authors: Haoxin Liu, Harshavardhan Kamarthi, Zhiyuan Zhao, Hongjie Chen, B. Aditya Prakash
  [Poster #31]
• Title: Prompt Relay: Inference-Time Temporal Prompt Routing for Multi-Event Video Generation
  Authors: Gordon Chen, Ziqi Huang, Ziwei Liu
  [Poster #31]
• Title: Time-to-Move: Training-Free Motion-Controlled Video Generation via Dual-Clock Denoising
  Authors: Assaf Singer, Noam Rotstein, Amir Mann, Ron Kimmel, Or Litany
  [Poster #32]
• Title: PISCO: Precise Video Instance Insertion with Sparse Control
  Authors: Xiangbo Gao, Renjie Li, Xinghao Chen, Yuheng Wu, Suofei Feng, Qing Yin
  [Poster #32]