AI Paper Atlas

Research map / 3D vision / Face and shape

Learning High-Fidelity Face Texture Completion Without Complete Face Texture

Jongyoo Kim, Jiaolong Yang, Xin Tong

ICCV 2021 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 18 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 image-space discriminator (ablation)DSD-GAN (texture-space discriminator only) · FaceScapeSSIM (avg): 0.6888 -> 0.7684Improved
add image-space discriminator (ablation)DSD-GAN (texture-space discriminator only) · FaceScapeFID: 43.0560 -> 3.3124Improved
add image-space discriminator (ablation)DSD-GAN (texture-space discriminator only) · FaceScapePerceptual similarity (avg): 0.6663 -> 0.7767Improved
add texture-space discriminator (ablation)DSD-GAN (image-space discriminator only) · FaceScapeSSIM (avg): 0.7582 -> 0.7684Improved
add texture-space discriminator (ablation)DSD-GAN (image-space discriminator only) · FaceScapeFID: 9.9678 -> 3.3124Improved
add texture-space discriminator (ablation)DSD-GAN (image-space discriminator only) · FaceScapePerceptual similarity (avg): 0.7682 -> 0.7767Improved
add coordinate regression to texture-space discriminator (ablation)DSD-GAN (texture-space discriminator only) · FaceScapeSSIM (avg): 0.6758 -> 0.6888Improved
add coordinate regression to texture-space discriminator (ablation)DSD-GAN (texture-space discriminator only) · FaceScapeFID: 56.4223 -> 43.0560Improved
add coordinate regression to texture-space discriminator (ablation)DSD-GAN (texture-space discriminator only) · FaceScapePerceptual similarity (avg): 0.6290 -> 0.6663Improved
train with unpaired face photos (DSD-GAN) instead of supervised on complete BFM texturestexture completion generator · FaceScapeSSIM (avg): 0.7434 -> 0.7684Improved
train with unpaired face photos (DSD-GAN) instead of supervised on complete BFM texturestexture completion generator · FaceScapeFID: 17.2121 -> 3.3124Improved
train with unpaired face photos (DSD-GAN) instead of supervised on Multi-PIE texturestexture completion generator · FaceScapeFID: 30.3546 -> 3.3124Improved

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