AI Paper Atlas

Research map / Video / Video generation

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

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

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 71 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on dynamic real videos with SfM camera annotations in addition to static data (ablation)CameraCtrl II · single-clip ablationMotion strength: 129.40 -> 306.99Improved
add scale calibration to metric space (ablation)RealCam dataset · single-clip ablationTransErr: 0.2121 -> 0.1830; RotErr 2.14 -> 1.74Improved
add camera trajectory distribution balancing (ablation)RealCam dataset · single-clip ablationRotErr: 4.56 -> 1.74Improved
inject camera only at initial layer instead of every DiT layer (ablation)CameraCtrl II · single-clip ablationMotion strength: 247.23 -> 306.99Improved
use single patchify layer instead of complex CameraCtrl-style encoder (ablation)CameraCtrl II · single-clip ablationGeometric consistency: 84.00 -> 86.50Improved
add joint training with camera-unlabeled video (ablation)CameraCtrl II · single-clip ablationMotion strength: 279.82 -> 306.99; TransErr 0.2098 -> 0.1830Improved
use global first-clip reference frame for relative poses (ablation)CameraCtrl II video extension · extension ablationAppearance consistency: 0.8032 -> 0.8654Improved
keep conditioning clips clean and compute loss only on generated clip (ablation)CameraCtrl II video extension · extension ablationFVD: 136.78 -> 112.46Improved
progressive distillation (NFEs 96 to 16)CameraCtrl II · distillationsample time and TransErr: 13.83 s -> 2.61 s; TransErr 0.1892 -> 0.2001Mixed
one-step APT distillationCameraCtrl II · distillationsample time and quality: 13.83 s -> 0.59 s; TransErr 0.1892 -> 0.2500Mixed
replace MotionCtrl/CameraCtrl with CameraCtrl III2V camera-controlled generation · 800-clip evalFVD: 199.53 -> 73.11Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy