AI Paper Atlas

Research map / 3D vision / Face and shape

HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details

Zenghao Chai, Tianke Zhang, Tianyu He, Xu Tan, Tadas Baltrusaitis, HsiangTao Wu, Runnan Li, Sheng Zhao, Chun Yuan, Jiang Bian

ICCV 2023 · 3D vision › Face and shape · approach: 3D morphable face model regression · 33 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
train with ground-truth labels from synthetic data (coarse shape) (ablation)HiFace coarse · REALY frontal-viewall-region error (mm): 1.558 -> 1.297Improved
train with ground-truth labels from synthetic data (detail) (ablation)HiFace detail · REALY frontal-viewall-region error (mm): 1.600 -> 1.275Improved
add static detail factor to the detail model (ablation)HiFace detail · REALY frontal-viewall-region error (mm): 1.295 -> 1.275Improved
add dynamic detail factor to the detail model (ablation)HiFace detail · REALY frontal-viewall-region error (mm): 1.292 -> 1.275Improved
add dynamic factor to the detail model (side view) (ablation)HiFace detail · REALY side-viewall-region error (mm): 1.318 -> 1.308Improved
add detail reconstruction on top of coarse shapeHiFace · REALY frontal-viewall-region error (mm): 1.297 -> 1.275Improved
image-level-supervised detail modeling (DECA, EMOCA) added to coarse shapeDECA/EMOCA · REALY frontal-viewall-region error (mm): 2.010 -> 2.210 (DECA); 2.103 -> 2.388 (EMOCA)Hurt
directly synthesize dynamic detail with U-Net instead of interpolating compressed/stretched maps (ablation)SD-DeTail · qualitative ablation (SD-1)visual qualityHurt
replace PCA displacement bases with U-Net decoders for static and dynamic detail (ablation)SD-DeTail · qualitative ablation (SD-2, SD-3)visual qualityHurt
add real-world data to synthetic training data (ablation)HiFace · qualitative ablationgeneralization to real imagesImproved
add KL coefficient loss L_kl (ablation)HiFace coarse shape · qualitative ablationgeneralization to real imagesImproved
add detail loss and age distillation loss L_kd (ablation)HiFace detail · qualitative ablationdetail qualityImproved

Later papers that compared with this method

2 later accepted papers report HiFace as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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