mlsanityData to 14 Oct 2026

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

arXiv 2503.10592 ↗First posted 13 Mar 2025cs.CVcited by 98

On the map: Diffusion models → Video generation

Abstract (arXiv)

This paper introduces CameraCtrl II, a framework that enables large-scale dynamic scene exploration through a camera-controlled video diffusion model. Previous camera-conditioned video generative models suffer from diminished video dynamics and limited range of viewpoints when generating videos with large camera movement. We take an approach that progressively expands the generation of dynamic scenes -- first enhancing dynamic content within individual video clip, then extending this capability to create seamless explorations across broad viewpoint ranges. Specifically, we construct a dataset featuring a large degree of dynamics with camera parameter annotations for training while designing a lightweight camera injection module and training scheme to preserve dynamics of the pretrained models. Building on these improved single-clip techniques, we enable extended scene exploration by allowing users to iteratively specify camera trajectories for generating coherent video sequences. Experiments across diverse scenarios demonstrate that CameraCtrl Ii enables camera-controlled dynamic scene synthesis with substantially wider spatial exploration than previous approaches.

Key facts. Cited by 98 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 64 of its 75 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

64 of 75 references.

Closest ancestors · 20

Same direction, newest first

  1. 2025Diffusion Adversarial Post-Training for One-Step Video Generation14 Jan
  2. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers27 Nov
  3. 2024CamI2V: Camera-Controlled Image-to-Video Diffusion Model21 Oct
  4. 2024Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention14 Oct
  5. 2024Diffusion Models Are Real-Time Game Engines27 Aug
  6. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  7. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control17 Jul
  8. 2024Training-free Camera Control for Video Generation14 Jun
  9. 2024Vivid-ZOO: Multi-View Video Generation with Diffusion Model12 Jun
  10. 2024CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation4 Jun
  11. 2024Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control27 May
  12. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generation2 Apr
8 more
  1. 2024Latte: Latent Diffusion Transformer for Video Generation5 Jan
  2. 2023Photorealistic Video Generation with Diffusion Models11 Dec
  3. 2023SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models28 Nov
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets25 Nov
  5. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation9 Oct
  6. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
  7. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models18 Apr
  8. 2022Video Diffusion Models7 Apr

Other references · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2022Classifier-Free Diffusion Guidancecited by 5,847
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  7. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  8. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  9. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  10. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  11. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,177
  12. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
32 more
  1. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  2. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  3. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 580
  4. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  5. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  6. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  7. 2024Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teacherscited by 393
  8. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  9. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 296
  10. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  11. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  12. 2021Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptionscited by 226
  13. 2024Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modelingcited by 211
  14. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 202
  15. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  16. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 168
  17. 2023WonderJourney: Going from Anywhere to Everywherecited by 158
  18. 2025GameFactory: Creating New Games with Generative Interactive Videoscited by 130
  19. 2024Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesiscited by 105
  20. 2018Unsupervised Training for 3D Morphable Model Regressioncited by 100
  21. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 99
  22. 2024SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpointscited by 93
  23. 2022InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Imagescited by 82
  24. 2024The Matrix: Infinite-Horizon World Generation with Real-Time Moving Controlcited by 80
  25. 20243DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generationcited by 71
  26. 2025RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Controlcited by 57
  27. 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
  28. 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
  29. 2024Generative Gaussian Splatting for Unbounded 3D City Generationcited by 44
  30. 2024I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strengthcited by 39
  31. 2025GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Trackingcited by 39
  32. 2022Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentationcited by 35

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 41; 2026: 57.

98 papers.

Sort:

By area:

  1. 2025Video World Models with Long-term Spatial Memorycited by 136
  2. 2025Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Conditioncited by 98
  3. 2025Controllable Video Generation: A Surveycited by 98
  4. 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 94
  5. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 90
  6. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 82
  7. 2025Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generationcited by 77
  8. 2025OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modelingcited by 62
  9. 2026Infinite Worlds with Versatile Interactionscited by 48
  10. 2025World-in-World: World Models in a Closed-Loop Worldcited by 47
  11. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 41
  12. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 40
38 more
  1. 2025Unified Camera Positional Encoding for Controlled Video Generationcited by 37
  2. 2025OmniNWM: Omniscient Driving Navigation World Modelscited by 33
  3. 2026VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Controlcited by 28
  4. 2026LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Modelscited by 28
  5. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
  6. 2026MosaicMem: Hybrid Spatial Memory for Controllable Video World Modelscited by 27
  7. 2025Epipolar Geometry Improves Video Generation Modelscited by 26
  8. 2026WorldCompass: Reinforcement Learning for Long-Horizon World Modelscited by 24
  9. 2025PanoWan: Lifting Diffusion Video Generation Models to 360deg with Latitude/Longitude-aware Mechanismscited by 23
  10. 2025EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidancecited by 21
  11. 2026INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modelingcited by 21
  12. 2025ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motionscited by 19
  13. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 18
  14. 2026PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inferencecited by 17
  15. 2026Latent Spatial Memory for Video World Modelscited by 17
  16. 2025SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observationscited by 16
  17. 2026AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memoriescited by 15
  18. 2025BulletTime: Decoupled Control of Time and Camera Pose for Video Generationcited by 14
  19. 20253D Scene Prompting for Scene-Consistent Camera-Controllable Video Generationcited by 13
  20. 2025Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpaintingcited by 11
  21. 2025DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generationcited by 11
  22. 2025How Much 3D Do Video Foundation Models Encode?cited by 11
  23. 2025SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Timecited by 11
  24. 2026AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Reportcited by 11
  25. 2025DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformercited by 10
  26. 2025Taming Camera-Controlled Video Generation with Verifiable Geometry Rewardcited by 10
  27. 2026SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generationcited by 10
  28. 2025Scaling Sequence-to-Sequence Generative Neural Renderingcited by 8
  29. 2025RelightMaster: Precise Video Relighting with Multi-plane Light Imagescited by 8
  30. 2025RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfercited by 7
  31. 2025The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Textcited by 7
  32. 2026ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creationcited by 7
  33. 2026InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Modelcited by 7
  34. 2026VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignmentcited by 7
  35. 2026Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generationcited by 7
  36. 2025PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attentioncited by 6
  37. 2025ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitionscited by 6
  38. 2026Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Controlcited by 6

50 most cited of 98 All 98 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control
  2. 2026PartiCam: Camera Controlled Video Generation with Reward Guidance
  3. 2026DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time
  4. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
  5. 2024Animate Your Motion: Turning Still Images into Dynamic Videos
  6. 2026MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
  7. 2025DreamJourney: Perpetual View Generation with Video Diffusion Models
  8. 2026AnyView: Synthesizing Any Novel View in Dynamic Scenes