CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Haoyu, Gu, Jiaxi, Chen, Haoran, Zheng, Qingping, Jin, Yeying, Yang, Hongyi, Cheng, Junqi, Zhang, Yuang, Lu, Zenghui, Yu, Huan, Jiang, Jie, Shu, Peng, Wu, Zuxuan, Jiang, Yu-Gang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916064221200384
author Zhao, Haoyu
Gu, Jiaxi
Chen, Haoran
Zheng, Qingping
Jin, Yeying
Yang, Hongyi
Cheng, Junqi
Zhang, Yuang
Lu, Zenghui
Yu, Huan
Jiang, Jie
Shu, Peng
Wu, Zuxuan
Jiang, Yu-Gang
author_facet Zhao, Haoyu
Gu, Jiaxi
Chen, Haoran
Zheng, Qingping
Jin, Yeying
Yang, Hongyi
Cheng, Junqi
Zhang, Yuang
Lu, Zenghui
Yu, Huan
Jiang, Jie
Shu, Peng
Wu, Zuxuan
Jiang, Yu-Gang
contents Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly inject numerical camera parameters into the diffusion backbone often fail to bridge the gap between abstract coordinates and visual content, leading to structural distortions. To address this issue, we propose CameraNoise, a flow-to-noise warping method that encodes camera motion into a temporally coherent stochastic representation. Unlike conventional conditioning, CameraNoise embeds camera poses directly into the noise space. This decouples motion from scene appearance while faithfully preserving trajectory dynamics. Specifically, we introduce a novel Geometry-guided Reprojection Flow and a noise warping algorithm, which jointly preserve the Gaussian prior of diffusion and ensure consistent noise propagation under camera transformations. By integrating CameraNoise into the diffusion process, our framework delivers stable, high-fidelity videos. Extensive experiments demonstrate that our approach significantly outperforms prior methods in both visual quality and trajectory faithfulness. The project page and code are available at: https://gulucaptain.github.io/CameraNoise/.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30774
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping
Zhao, Haoyu
Gu, Jiaxi
Chen, Haoran
Zheng, Qingping
Jin, Yeying
Yang, Hongyi
Cheng, Junqi
Zhang, Yuang
Lu, Zenghui
Yu, Huan
Jiang, Jie
Shu, Peng
Wu, Zuxuan
Jiang, Yu-Gang
Computer Vision and Pattern Recognition
Precise camera pose control is critical for video diffusion, yet maintaining geometric consistency remains a challenge. Existing methods that directly inject numerical camera parameters into the diffusion backbone often fail to bridge the gap between abstract coordinates and visual content, leading to structural distortions. To address this issue, we propose CameraNoise, a flow-to-noise warping method that encodes camera motion into a temporally coherent stochastic representation. Unlike conventional conditioning, CameraNoise embeds camera poses directly into the noise space. This decouples motion from scene appearance while faithfully preserving trajectory dynamics. Specifically, we introduce a novel Geometry-guided Reprojection Flow and a noise warping algorithm, which jointly preserve the Gaussian prior of diffusion and ensure consistent noise propagation under camera transformations. By integrating CameraNoise into the diffusion process, our framework delivers stable, high-fidelity videos. Extensive experiments demonstrate that our approach significantly outperforms prior methods in both visual quality and trajectory faithfulness. The project page and code are available at: https://gulucaptain.github.io/CameraNoise/.
title CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.30774