ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding
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
- 2022Scalable Diffusion Models with Transformerscited by 6,054
- 2022Classifier-Free Diffusion Guidancecited by 5,847
- 2022Flow Matching for Generative Modelingcited by 5,702
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
- 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
- 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
- 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
- 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
- 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
- 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
- 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
- 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
38 more
- 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
- 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 580
- 2023CoTracker: It is Better to Track Togethercited by 522
- 2025VACE: All-in-One Video Creation and Editingcited by 479
- 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
- 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
- 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
- 2022Kubric: A scalable dataset generatorcited by 381
- 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
- 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 287
- 2024Rotary Position Embedding for Vision Transformercited by 236
- 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 228
- 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
- 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 207
- 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 204
- 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
- 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
- 2024SpatialTracker: Tracking Any 2D Pixels in 3D Spacecited by 181
- 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 179
- 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
- 2024CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generationcited by 166
- 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 163
- 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Modelscited by 161
- 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
- 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 154
- 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
- 2024Training-free Camera Control for Video Generationcited by 122
- 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 117
- 2024Round and Round We Go! What makes Rotary Positional Encodings useful?cited by 115
- 2025Cameras as Relative Positional Encodingcited by 105
- 2025Controllable Video Generation: A Surveycited by 98
- 2024EscherNet: A Generative Model for Scalable View Synthesiscited by 95
- 2025MEt3R: Measuring Multi-View Consistency in Generated Imagescited by 95
- 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 79
- 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
- 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 73
- 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
- 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
Citing papers per year: 2026: 11.
11 papers.
- 2026SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformerscited by 5
- 2026RealCam: Real-Time Novel-View Video Generation with Interactive Camera Controlcited by 3
- 2026Geo-Align: Video Generation Alignment via Metric Geometry Rewardcited by 3
- 2026SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cuescited by 2
- 2026MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generationcited by 2
- 2026Pano2World: End-to-End 3D Generation via Unified Multi-View Sequencescited by 2
- 2026TrajectoryMover: Generative Movement of Object Trajectories in Videoscited by 1
- 2026DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformerscited by 1
- 2026CameraAnything: Refilming Videos with Arbitrary Camera Controlcited by 1
- 2026CamWorldQA: Perceptual Quality Assessment of Camera-Controlled World Video Generationcited by 0
- 2026FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlowcited by 0
- 2026FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow3 Sep 2026
- 2026CamWorldQA: Perceptual Quality Assessment of Camera-Controlled World Video Generation19 Aug 2026
- 2026CameraAnything: Refilming Videos with Arbitrary Camera Control27 Jul 2026
- 2026Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences1 Jul 2026
- 2026DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers30 Jun 2026
- 2026SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers25 Jun 2026
- 2026MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation24 Jun 2026
- 2026SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues15 Jun 2026
- 2026Geo-Align: Video Generation Alignment via Metric Geometry Reward22 May 2026
- 2026RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control7 May 2026
- 2026TrajectoryMover: Generative Movement of Object Trajectories in Videos31 Mar 2026