AI Paper Atlas

Research map / Video / Video generation

CameraAnything: Refilming Videos with Arbitrary Camera Control

Yixuan Li, Yanhong Zeng, Ka Leong Cheng, Jiayi Zhu, Hanlin Wang, Wen Wang, Yihao Meng, Hao Ouyang, Qiuyu Wang, Yue Yu, Zidong Wang, Yiyuan Zhang and 2 more

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 4 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
use Plucker rays with AdaLN instead of linear camera vector with addition (ablation)CameraAnything · SyntheticPSNR: 15.62 -> 16.51Improved
use RoPE injection instead of AdaLN for Plucker rays (ablation)CameraAnything · SyntheticPSNR: 16.51 -> 16.66Improved
use RoPE instead of AdaLN (ablation)CameraAnything · SyntheticLPIPS: 0.368 -> 0.372Mixed
jointly train focal and resolution with extrinsics (ablation)CameraAnything · Synthetic extrinsic tasksPSNR: 14.00 -> 14.13No clear effect
add identity samples (decoupled control dimensions) (ablation)CameraAnything · Synthetic focal tasksPSNR: 15.94 -> 20.03Improved
add identity samples (decoupled control dimensions) (ablation)CameraAnything · Synthetic resolution tasksPSNR: 14.64 -> 20.05Improved
use CameraAnything vs ReCamMaster for camera accuracyCameraAnything · DAVISRotErr: 5.12 -> 2.76Improved
use CameraAnything vs ReCamMaster on VBenchCameraAnything · Synthetic / DAVISVBench consistency and flicker: DAVIS Flicker 0.9596 vs 0.9463Hurt
use CameraAnything vs VACE on subject/background consistencyCameraAnything · Synthetic resolution editingBackground consistency: 0.9225 -> 0.9100Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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