mlsanityData to 7 Oct 2026

ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions

arXiv 2512.10286 ↗First posted 11 Dec 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Shot transitions play a pivotal role in multi-shot video generation, as they determine the overall narrative expression and the directorial design of visual storytelling. However, recent progress has primarily focused on low-level visual consistency across shots, neglecting how transitions are designed and how cinematographic language contributes to coherent narrative expression. This often leads to mere sequential shot changes without intentional film-editing patterns. To address this limitation, we propose ShotDirector, an efficient framework that integrates parameter-level camera control and hierarchical editing-pattern-aware prompting. Specifically, we adopt a camera control module that incorporates 6-DoF poses and intrinsic settings to enable precise camera information injection. In addition, a shot-aware mask mechanism is employed to introduce hierarchical prompts aware of professional editing patterns, allowing fine-grained control over shot content. Through this design, our framework effectively combines parameter-level conditions with high-level semantic guidance, achieving film-like controllable shot transitions. To facilitate training and evaluation, we construct ShotWeaver40K, a dataset that captures the priors of film-like editing patterns, and develop a set of evaluation metrics for controllable multi-shot video generation. Extensive experiments demonstrate the effectiveness of our framework.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 48 of its 55 references that are in the map. First posted on arXiv 11 Dec 2025.

Builds on

48 of 55 references.

References · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  8. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  9. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  10. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  11. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  12. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
36 more
  1. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  2. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  3. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  4. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  5. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generatorscited by 666
  6. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 536
  7. 2023InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generationcited by 488
  8. 2025VACE: All-in-One Video Creation and Editingcited by 467
  9. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  10. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  11. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  12. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
  13. 2024StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generationcited by 240
  14. 2023SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Predictioncited by 231
  15. 2023A Survey on Video Diffusion Modelscited by 203
  16. 2020TransNet V2: An effective deep network architecture for fast shot transition detectioncited by 166
  17. 2024CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generationcited by 163
  18. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  19. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  20. 2025Phantom: Subject-consistent video generation via cross-modal alignmentcited by 126
  21. 2024Training-free Camera Control for Video Generationcited by 119
  22. 2025Long Context Tuning for Video Generationcited by 110
  23. 2025One-Minute Video Generation with Test-Time Trainingcited by 100
  24. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 97
  25. 2024SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpointscited by 92
  26. 2023Animate-A-Story: Storytelling with Retrieval-Augmented Video Generationcited by 89
  27. 2024MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequencecited by 85
  28. 2024Vlogger: Make Your Dream A Vlogcited by 70
  29. 2024VideoStudio: Generating Consistent-Content and Multi-Scene Videoscited by 62
  30. 2024A Survey on Long Video Generation: Challenges, Methods, and Prospectscited by 40
  31. 2024I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strengthcited by 38
  32. 2025ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Modelscited by 37
  33. 2025CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Modelscited by 26
  34. 2025Mask2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generationcited by 24
  35. 2025MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generationcited by 16
  36. 2025Cut2Next: Generating Next Shot via In-Context Tuningcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.