CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback

• URL: http://arxiv.org/abs/2601.16214v1
• Date: Thu, 22 Jan 2026 18:59:56 GMT
• Title: CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback
• Authors: Wenhang Ge, Guibao Shen, Jiawei Feng, Luozhou Wang, Hao Lu, Xingye Tian, Xin Tao, Ying-Cong Chen,
• Abstract summary: We build upon Reward Feedback Learning and aim to further improve camera controllability.<n>Current reward models lack the capacity to assess video-camera alignment.<n>We introduce an efficient camera-aware 3D decoder that decodes video latent into 3D representations for reward quantization.
• Score: 43.174121093566264
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in camera-controlled video diffusion models have significantly improved video-camera alignment. However, the camera controllability still remains limited. In this work, we build upon Reward Feedback Learning and aim to further improve camera controllability. However, directly borrowing existing ReFL approaches faces several challenges. First, current reward models lack the capacity to assess video-camera alignment. Second, decoding latent into RGB videos for reward computation introduces substantial computational overhead. Third, 3D geometric information is typically neglected during video decoding. To address these limitations, we introduce an efficient camera-aware 3D decoder that decodes video latent into 3D representations for reward quantization. Specifically, video latent along with the camera pose are decoded into 3D Gaussians. In this process, the camera pose not only acts as input, but also serves as a projection parameter. Misalignment between the video latent and camera pose will cause geometric distortions in the 3D structure, resulting in blurry renderings. Based on this property, we explicitly optimize pixel-level consistency between the rendered novel views and ground-truth ones as reward. To accommodate the stochastic nature, we further introduce a visibility term that selectively supervises only deterministic regions derived via geometric warping. Extensive experiments conducted on RealEstate10K and WorldScore benchmarks demonstrate the effectiveness of our proposed method. Project page: \href{https://a-bigbao.github.io/CamPilot/}{CamPilot Page}.

Related papers

• Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians [7.051077403685518]
  Humans excel at forecasting the future dynamics of a scene given just a single image.<n>Video generation models that can mimic this ability are an essential component for intelligent systems.<n>Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation.
  arXiv  Detail & Related papers  (2026-01-02T13:04:47Z)
• 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)
• GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control [88.90505842498823]
  We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency.<n>Our results demonstrate more precise camera control than prior work, as well as state-of-the-art results in sparse-view novel view synthesis.
  arXiv  Detail & Related papers  (2025-03-05T18:59:50Z)
• AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers [66.29824750770389]
  We analyze camera motion from a first principles perspective, uncovering insights that enable precise 3D camera manipulation.<n>We compound these findings to design the Advanced 3D Camera Control (AC3D) architecture.
  arXiv  Detail & Related papers  (2024-11-27T18:49:13Z)
• Generating 3D-Consistent Videos from Unposed Internet Photos [68.944029293283]
  We train a scalable, 3D-aware video model without any 3D annotations such as camera parameters. Our results suggest that we can scale up scene-level 3D learning using only 2D data such as videos and multiview internet photos.
  arXiv  Detail & Related papers  (2024-11-20T18:58:31Z)
• 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)
• CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation [117.16677556874278]
  We introduce CamCo, which allows fine-grained Camera pose Control for image-to-video generation. To enhance 3D consistency in the videos produced, we integrate an epipolar attention module in each attention block. Our experiments show that CamCo significantly improves 3D consistency and camera control capabilities compared to previous models.
  arXiv  Detail & Related papers  (2024-06-04T17:27:19Z)

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.