AI Paper Atlas

Research map / 3D vision / Face and shape

Pose-Invariant Face Alignment With a Single CNN

Amin Jourabloo, Mao Ye, Xiaoming Liu, Liu Ren

ICCV 2017 · 3D vision › Face and shape · approach: 3D morphable face model regression · 123 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 visualization layers during training (ablation)Proposed single CNN · AFLWNME (%): 7.18 -> 4.45Improved
add input image and feature maps (I,F,V) versus (I,V) only (ablation)Visualization block inputs · AFLWNME (%): 5.06 -> 4.45Improved
add input image to (F,V) block inputs (ablation)Visualization block inputs · AFLWNME (%): 4.48 -> 4.45Improved
add mask in visualization layer (ablation)Visualization layer · AFLWNME (%): 5.31 -> 4.45Improved
use more complicated mask 2 instead of original mask (ablation)Visualization layer · AFLWNME (%): 4.45 -> 4.49No clear effect
use 6 blocks with 2 conv layers instead of 4 blocks with 3 conv layers (ablation)Proposed CNN (12 conv layers) · AFLWNME (%): 4.61 -> 4.45Improved
use 6 blocks with 2 conv layers instead of 3 blocks with 4 conv layers (ablation)Proposed CNN (12 conv layers) · AFLWNME (%): 4.83 -> 4.45Improved
add more visualization blocks (sequentially 1 to 6) (ablation)Proposed · AFLWNME (%): 9.26 -> 4.45Improved
add 5% noise to the fully connected parameters of the last block at test time (ablation)Proposed · AFLWNME (%): 4.45 -> 5.16Hurt
add 5% noise to the fully connected parameters of the first block at test time (ablation)Proposed · AFLWNME (%): 4.45 -> 4.46No clear effect
use proposed method instead of LPFALarge-pose face alignment · AFWMAPE: 7.43 -> 6.27Improved
use proposed method instead of 3DDFA+SDM on challenging setFace alignment · 300W ChallengingNME (%): 9.56 -> 9.88Mixed

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