AI Paper Atlas

Research map / 3D vision / Face and shape

Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction

Barış Geçer, Stylianos Ploumpis, Irene Kotsia, Stefanos P. Zafeiriou

TPAMI 2021 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 69 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 identity losses L_id, L_id-hat and L_con together (ablation)GANFit · MICC cooperativeshape error (mm): 1.20 -> 0.95Improved
add L_id-hat (ablation)GANFit · MICC cooperativeshape error (mm): 1.07 -> 0.95Improved
add L_id alone (ablation)GANFit · MICC cooperativeshape error (mm): 0.96 -> 0.95No clear effect
add L_con (ablation)GANFit · MICC cooperativeshape error (mm): 0.94 -> 0.95No clear effect
add pixel loss L_pix (ablation)GANFit · MICC cooperativeshape error (mm): 0.94 -> 0.95No clear effect
add landmark loss L_lan (ablation)GANFit · MICC cooperativeshape error (mm): 0.91 -> 0.95Hurt
add shape regularizer Reg(p_s) (ablation)GANFit · MICC cooperativeshape error (mm): 1.03 -> 0.95Improved
add expression regularizer Reg(p_e) (ablation)GANFit · MICC cooperativeshape error (mm): 0.95 -> 0.95No clear effect
add Reg(p_l) lighting regularizer (ablation)GANFit · MICC cooperativeshape error (mm): 0.96 -> 0.95No clear effect
initialise GANFit with FastGANFit regression (GANFit++)GANFit · MICC outdoorshape error (mm): 0.95 -> 0.94No clear effect
replace VAE texture model with GANtexture model · UV texture, Ours (9358)FID: 120.44 -> 2.95Improved
replace PCA texture model with GANtexture model · UV texture, Ours (9358)FID: 65.80 -> 2.95Improved

Later papers that compared with this method

1 later accepted paper reports Fast-GANFit 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