AI Paper Atlas

Research map / 3D vision / Face and shape

Towards Metrical Reconstruction of Human Faces

Wojciech Zielonka, Timo Bolkart, Justus Thies

ECCV 2022 · 3D vision › Face and shape · approach: 3D morphable face model regression · 202 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
use ArcFace instead of FaceNet as identity encoder (ablation)MICA · Stirling (metrical, HQ)mean error (mm): 1.65 -> 1.52Improved
fine-tune last ResNet layer (L4) of ArcFace (ablation)MICA frozen ArcFace · Stirling (metrical, HQ)mean error (mm): 1.52 -> 1.35Improved
fine-tune all ArcFace layers instead of only L4 (ablation)MICA · Stirling (metrical, HQ)mean error (mm): 1.35 -> 1.42Hurt
fine-tune DECA encoder fully on unified dataset (ablation)DECA · Stirling (metrical, HQ)mean error (mm): 1.58 -> 1.82Hurt
use ArcFace features instead of fine-tuned DECA encoder (ablation)DECA fine-tuned · Stirling (metrical, HQ)mean error (mm): 1.82 -> 1.35Improved
increase FLAME principal components from 50 to 300 (ablation)MICA decoder · Stirling (metrical, HQ)mean error (mm): 1.41 -> 1.35Improved
add LYHM dataset to training data (ablation)MICA · Stirling (metrical, HQ)mean error (mm): 1.43 -> 1.35Improved
add LYHM dataset to training data (ablation)MICA · Stirling (metrical, LQ)mean error (mm): 1.51 -> 1.46Improved
add FaceWarehouse dataset to training data (ablation)MICA · Stirling (metrical, HQ)mean error (mm): 1.36 -> 1.35No clear effect
use FLAME decoder instead of model-free SIREN decoder (ablation)MICA · Stirling (metrical, HQ)mean error (mm): 1.39 -> 1.35No clear effect
evaluate with scale optimization (non-metrical) instead of rigid alignmentAverage FLAME face · NoWmean error (mm): 1.92 -> 1.53Improved
replace DECA with MICA shape predictionDECA · NoW (metrical)mean error (mm): 1.80 -> 1.37Improved

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