AI Paper Atlas

Research map / 3D vision / Face and shape

Towards High Fidelity Face Frontalization in the Wild

Jie Cao, Yibo Hu, Hongwen Zhang, Ran He, Zhenan Sun

IJCV 2019 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 102 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
frontalize with HF-PIM instead of PIMPIM · Multi-PIE +-90 degrank-1: 86.5 -> 92.32Improved
frontalize with HF-PIM instead of CAPG-GANCAPG-GAN · Multi-PIE +-90 degrank-1: 66.1 -> 92.32Improved
frontalize with HF-PIM instead of PIMPIM · IJB-Averification at FAR=0.001: 87.5 -> 89.7Improved
frontalize with HF-PIM instead of PIMPIM · IJB-Arank-1: 94.4 -> 96.1Improved
frontalize with HF-PIM instead of CAPG-GANCAPG-GAN · LFWverification accuracy: 99.37 -> 99.41No clear effect
frontalize with HF-PIM instead of Light CNN aloneLight CNN · LFWverification accuracy: 99.39 -> 99.41No clear effect

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