Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
- URL: http://arxiv.org/abs/2605.15182v1
- Date: Thu, 14 May 2026 17:58:26 GMT
- Title: Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
- Abstract summary: We propose a simple interface that turns camera-induced warps into camera-warped pseudo-history.<n>We align its positional encoding with the target frames being denoised and remove warped-history tokens without valid source observations.<n>Our method improves camera adherence, visual quality, and motion dynamics without test-time optimization or target-video adaptation.
- Score: 19.675672131137382
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Camera-controlled video generation has made substantial progress, enabling generated videos to follow prescribed viewpoint trajectories. However, existing methods usually learn camera-specific conditioning through camera encoders, control branches, or attention and positional-encoding modifications, which often require post-training on large-scale camera-annotated videos. Training-free alternatives avoid such post-training, but often shift the cost to test-time optimization or extra denoising-time guidance. We propose Warp-as-History, a simple interface that turns camera-induced warps into camera-warped pseudo-history with target-frame positional alignment and visible-token selection. Given a target camera trajectory, we construct camera-warped pseudo-history from past observations and feed it through the model's visual-history pathway. Crucially, we align its positional encoding with the target frames being denoised and remove warped-history tokens without valid source observations. Without any training, architectural modification, or test-time optimization, this interface reveals a non-trivial zero-shot capability of a frozen video generation model to follow camera trajectories. Moreover, lightweight offline LoRA finetuning on only one camera-annotated video further improves this capability and generalizes to unseen videos, improving camera adherence, visual quality, and motion dynamics without test-time optimization or target-video adaptation. Extensive experiments on diverse datasets confirm the effectiveness of our method.
Related papers
- Geo-Align: Video Generation Alignment via Metric Geometry Reward [53.65904111864641]
Geo-Align is the first Reinforcement Learning framework specifically designed for camera-controlled video re-rendering.<n>Built upon a pretrained model, we optimize the model through a scale-aware perceptual reward mechanism.<n>Experiments demonstrate that Geo-Align consistently outperforms existing supervised learning baselines in both precise camera controllability and visual fidelity.
arXiv Detail & Related papers (2026-05-22T17:59:43Z) - Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation [49.12018869332346]
InfCam is a camera-controlled video-to-video generation framework with high pose fidelity.<n>The framework integrates two key components: (1) infinite homography warping, which encodes 3D camera rotations directly within the 2D latent space of a video diffusion model.
arXiv Detail & Related papers (2025-12-18T20:03:05Z) - ReCamMaster: Camera-Controlled Generative Rendering from A Single Video [72.42376733537925]
ReCamMaster is a camera-controlled generative video re-rendering framework.<n>It reproduces the dynamic scene of an input video at novel camera trajectories.<n>Our method also finds promising applications in video stabilization, super-resolution, and outpainting.
arXiv Detail & Related papers (2025-03-14T17:59:31Z) - CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models [89.63787060844409]
CameraCtrl II is a framework that enables large-scale dynamic scene exploration through a camera-controlled video diffusion model.<n>We take an approach that progressively expands the generation of dynamic scenes.
arXiv Detail & Related papers (2025-03-13T17:42:01Z) - Learning Camera Movement Control from Real-World Drone Videos [25.10006841389459]
Existing AI videography methods struggle with limited appearance diversity in simulation training.<n>We propose a scalable method that involves collecting real-world training data.<n>We show that our system effectively learns to perform challenging camera movements.
arXiv Detail & Related papers (2024-12-12T18:59:54Z) - Image Conductor: Precision Control for Interactive Video Synthesis [90.2353794019393]
Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements.
Image Conductor is a method for precise control of camera transitions and object movements to generate video assets from a single image.
arXiv Detail & Related papers (2024-06-21T17:55:05Z) - Training-free Camera Control for Video Generation [15.79168688275606]
We propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models.<n>Our method does not require any supervised finetuning on camera-annotated datasets or self-supervised training via data augmentation.<n>It can be plug-and-play with most pretrained video diffusion models and generate camera-controllable videos with a single image or text prompt as input.
arXiv Detail & Related papers (2024-06-14T15:33:00Z) - Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control [70.17137528953953]
Collaborative video diffusion (CVD) is trained on top of a state-of-the-art camera-control module for video generation.
CVD generates multiple videos rendered from different camera trajectories with significantly better consistency than baselines.
arXiv Detail & Related papers (2024-05-27T17:58:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.