AI Paper Atlas

Research map / 3D vision / Face and shape

FSGAN: Subject Agnostic Face Swapping and Reenactment

Yuval Nirkin, Yosi Keller, Tal Hassner

ICCV 2019 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 742 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 completion network Gc to Gr (ablation)FSGAN (Gr) · FaceForensics++ ablation (first 100 frames of 500 videos)pose Euler error: 3.16 -> 3.21Hurt
add completion network Gc to Gr (ablation)FSGAN (Gr) · FaceForensics++ ablation (first 100 frames of 500 videos)landmark error: 22.6 -> 24.5Hurt
add blending network Gb to Gr (ablation)FSGAN (Gr) · FaceForensics++ ablation (first 100 frames of 500 videos)pose Euler error: 3.16 -> 2.75Improved
add blending network Gb to Gr (ablation)FSGAN (Gr) · FaceForensics++ ablation (first 100 frames of 500 videos)SSIM: 0.54 -> 0.52Hurt
add completion network Gc to Gr+Gb (ablation)FSGAN (Gr+Gb) · FaceForensics++ ablation (first 100 frames of 500 videos)pose Euler error: 2.75 -> 2.49Improved
add completion network Gc to Gr+Gb (ablation)FSGAN (Gr+Gb) · FaceForensics++ ablation (first 100 frames of 500 videos)landmark error: 23.6 -> 22.2Improved
add blending network Gb to Gr+Gc (ablation)FSGAN (Gr+Gc) · FaceForensics++ ablation (first 100 frames of 500 videos)pose Euler error: 3.21 -> 2.49Improved
add blending network Gb to Gr+Gc (ablation)FSGAN (Gr+Gc) · FaceForensics++ ablation (first 100 frames of 500 videos)SSIM: 0.54 -> 0.51Hurt
use FSGAN instead of Nirkin et al.Nirkin et al. · FaceForensics++ swapping (first 100 frames of 500 videos)pose Euler error: 3.15 -> 2.49Improved
use FSGAN instead of Nirkin et al.Nirkin et al. · FaceForensics++ swapping (first 100 frames of 500 videos)landmark error: 26.5 -> 22.2Improved
use FSGAN instead of DeepFakesDeepFakes · FaceForensics++ swapping (first 100 frames of 500 videos)pose Euler error: 4.05 -> 2.49Improved
use FSGAN instead of DeepFakesDeepFakes · FaceForensics++ swapping (first 100 frames of 500 videos)SSIM: 0.50 -> 0.51No clear effect

Later papers that compared with this method

2 later accepted papers report FSGAN as a baseline in their results tables; 2 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