AI Paper Atlas

Research map / Video / Video generation

RIGID: Recurrent GAN Inversion and Editing of Real Face Videos

Yangyang Xu, Shengfeng He, Kwan-Yee K. Wong, Ping Luo

ICCV 2023 · Video › Video generation · approach: Diffusion-based video editing · 13 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
add temporal compensated code from recurrent encoder (ablation)RIGID · RAVDESS-72 video inversionWE (warp error): 106.52 -> 84.62Improved
add learned noise map (ablation)RIGID · RAVDESS-72 video inversionMSE (x100): 2.28 -> 1.04Improved
add latent frequency disentanglement (share latter latent code across frames) (ablation)RIGID · RAVDESS-72 video inversionWE (warp error): 103.61 -> 84.62Improved
add temporal consistency loss L_tc (ablation)RIGID · RAVDESS-72 video inversionWE (warp error): 122.08 -> 84.62Improved
add in-between frame composition constraint (ablation)RIGID · RAVDESS-72 video editingFVD: 299.12 -> 198.54Improved
add in-between frame composition constraint (ablation)RIGID · RAVDESS-72 video inversionWE (warp error): 705.22 -> 84.62Improved
add in-between frame composition constraint on MSE (ablation)RIGID · RAVDESS-72 video inversionMSE (x100): 0.93 -> 1.04Hurt
use learned recurrent encoder instead of per-video optimization (STIT)RIGID · video inversion inference timeIT (s): 851.5 -> 54.5Improved
RIGID versus optimization-based STIT/TCSVE on reconstructionRIGID · RAVDESS-72 video inversionMSE (x100): 1.04 vs 0.99Hurt

Later papers that compared with this method

1 later accepted paper reports RIGID as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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