AI Paper Atlas

Research map / 3D vision / Face and shape

AvatarMe++: Facial Shape and BRDF Inference With Photorealistic Rendering-Aware GANs

Alexandros Lattas, Stylianos Moschoglou, Stylianos Ploumpis, Barış Geçer, Abhijeet Ghosh, Stefanos P. Zafeiriou

TPAMI 2021 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 71 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 rendering loss (ablation)single-network AvatarMe++ · test set T reflectanceMSE: 0.0080 -> 0.0075Improved
add whole low-res texture input (ablation)single-network AvatarMe++ · test set T reflectanceMSE: 0.0075 -> 0.0066Improved
add random rendering environment (ablation)AvatarMe++ · test set T reflectanceMSE: 0.0066 -> 0.0055Improved
add multiple random environments (ablation)AvatarMe++ · test set T reflectanceMSE: 0.0055 -> 0.0048Improved
add self-occlusion autoencoder (ablation)AvatarMe++ · test set T reflectanceMSE: 0.0048 -> 0.0043Improved
replace four networks with a single network (ablation)AvatarMe · test set T reflectanceMSE: 0.0079 -> 0.0080No clear effect
add 50%/25%/25% scene variation in rendering loss (ablation)AvatarMe++ · test set TRecon. MSE: 0.0055 -> 0.0043Improved
increase scene variation to 75%/50%/50% (ablation)AvatarMe++ · test set TRecon. MSE: 0.0043 -> 0.0051Hurt
use 2 rendering scenes instead of 1 (ablation)AvatarMe++ · test set TRecon. MSE: 0.0054 -> 0.0045Improved
use 3 rendering scenes instead of 2 (ablation)AvatarMe++ · test set TRecon. MSE: 0.0045 -> 0.0043Improved
set rendering loss weight lambda_R to 0.3 (ablation)AvatarMe++ · test set Treflectance MSEImproved
upgrade AvatarMe to AvatarMe++ versus prior methodsAvatarMe++ · in-the-wild reconstructionsPSNR (Albedo): 24.05 -> 26.18Improved

Later papers that compared with this method

1 later accepted paper reports AvatarMe++ 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