# CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

Source: [CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models](<https://www.sota2.com/research/paper/68fa77631e209131cea72ec5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:17:49.742Z

Authors: Hao He, Ceyuan Yang, Shanchuan Lin, Yinghao Xu, Meng Wei, Liangke Gui, Qi Zhao, Gordon Wetzstein, Lu Jiang, Hongsheng Li

Published: 2025-03-13T17:42:01.000Z

## Abstract

This paper introduces CameraCtrl II, a framework that enables large-scale dynamic scene exploration through a camera-controlled video diffusion model. Previous camera-conditioned video generative models suffer from diminished video dynamics and limited range of viewpoints when generating videos with large camera movement. We take an approach that progressively expands the generation of dynamic scenes -- first enhancing dynamic content within individual video clip, then extending this capability to create seamless explorations across broad viewpoint ranges. Specifically, we construct a dataset featuring a large degree of dynamics with camera parameter annotations for training while designing a lightweight camera injection module and training scheme to preserve dynamics of the pretrained models. Building on these improved single-clip techniques, we enable extended scene exploration by allowing users to iteratively specify camera trajectories for generating coherent video sequences. Experiments across diverse scenarios demonstrate that CameraCtrl Ii enables camera-controlled dynamic scene synthesis with substantially wider spatial exploration than previous approaches.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Camera-motion transfer on Scale-calibrated camera-motion transfer evaluation suite Average of Tabletop, Human/Room, Architectural, and Cosmic regimes (test)](<https://www.sota2.com/research/sota/camera-motion-transfer-on-scale-calibrated-camera-motion-transfer-evaluation-suite-average-of-tabletop-human-room-architectural-and-cosmic-regimes-test.md>): Camera-motion transfer; Scale-calibrated camera-motion transfer evaluation suite Average of Tabletop, Human/Room, Architectural, and Cosmic regimes (test); PCE: 0.39.

- [Camera-controlled Video Generation on RealEstate10K (FVD, PSNR, SSIM, LPIPS, ATE, RTE, RRE)](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-realestate10k-fvd-psnr-ssim-lpips-ate-rte-rre.md>): Camera-controlled Video Generation; RealEstate10K; FVD: 207.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.10592>)

[PDF](<https://arxiv.org/pdf/2503.10592.pdf>)
