AI Paper Atlas

Research map / Video / Video generation

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Jianhong Bai, Menghan Xia, Xiao Fu, Xintao Wang, Lianrui Mu, Jinwen Cao, Zuozhu Liu, Haoji Hu, Xiang Bai, Pengfei Wan, Di Zhang

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 203 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 frame concatenation instead of channel concatenation for video conditioning (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (conditioning ablation)FID: 74.09 -> 57.10Improved
use frame concatenation instead of channel concatenation for video conditioning (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (conditioning ablation)Mat. Pix.(K): 521.10 -> 906.03Improved
use frame concatenation instead of view concatenation for video conditioning (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (conditioning ablation)FID: 80.51 -> 57.10Improved
use frame concatenation instead of view concatenation for video conditioning (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (conditioning ablation)FVD-V: 177.68 -> 90.38Improved
use frame concatenation instead of view concatenation for video conditioning (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (conditioning ablation)CLIP-T: 34.66 -> 34.53No clear effect
add noise to conditional video latent (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (training strategy ablation)FID: 66.67 -> 65.17Improved
fine-tune only 3D attention layers (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (training strategy ablation)FID: 66.67 -> 59.47Improved
drop source latent with 20% probability for T2V and I2V training (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (training strategy ablation)FID: 66.67 -> 62.39Improved
combine noise, 3D attention tuning and latent dropping (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (training strategy ablation)FVD: 171.80 -> 122.74Improved
train on high-quality diverse data instead of toy data (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (training data ablation)FID: 69.35 -> 57.10Improved
train on high-quality diverse data instead of toy data (ablation)ReCamMaster · WebVid 1000 videos x 10 trajectories (training data ablation)FVD-V: 89.58 -> 90.38No clear effect

Later papers that compared with this method

22 later accepted papers report ReCamMaster* as a baseline in their results tables; 20 of them report a better number on most of the results they share with it.

14 more not listed.

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