mlsanityData to 14 Oct 2026

ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding

arXiv 2511.19827 ↗First posted 25 Nov 2025cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE in previous works by aligning the spatiotemporal positions of the input video and the target retake. Moreover, we introduce Rotary Camera Encoding (RoCE), a camera-conditioned RoPE phase shift that captures and integrates multi-view relationships within and across the input and target videos. By integrating camera conditions into RoPE, our method generalizes to out-of-distribution camera trajectories and video lengths, yielding improved dynamic object localization and static background preservation. Extensive experiments further demonstrate significant improvements in camera controllability, geometric consistency, and video quality across various trajectories and lengths.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 71 of its 75 references that are in the map. First posted on arXiv 25 Nov 2025.

Builds on

71 of 75 references.

References · 71

  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2022Classifier-Free Diffusion Guidancecited by 5,847
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  8. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  9. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  10. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  11. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  12. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
38 more
  1. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  2. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 580
  3. 2023CoTracker: It is Better to Track Togethercited by 522
  4. 2025VACE: All-in-One Video Creation and Editingcited by 479
  5. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
  6. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  7. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  8. 2022Kubric: A scalable dataset generatorcited by 381
  9. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  10. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 287
  11. 2024Rotary Position Embedding for Vision Transformercited by 236
  12. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 228
  13. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  14. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 207
  15. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 204
  16. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
  17. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  18. 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 181
  19. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 179
  20. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  21. 2024CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generationcited by 166
  22. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 163
  23. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Modelscited by 161
  24. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  25. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 154
  26. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  27. 2024Training-free Camera Control for Video Generationcited by 122
  28. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 117
  29. 2024Round and Round We Go! What makes Rotary Positional Encodings useful?cited by 115
  30. 2025Cameras as Relative Positional Encodingcited by 105
  31. 2025Controllable Video Generation: A Surveycited by 98
  32. 2024EscherNet: A Generative Model for Scalable View Synthesiscited by 95
  33. 2025MEt3R: Measuring Multi-View Consistency in Generated Imagescited by 95
  34. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 79
  35. 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
  36. 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 73
  37. 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
  38. 2024ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuningcited by 70

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 11.

11 papers.