AI Paper Atlas

Research map / 3D vision / Face and shape

M2FPA: A Multi-Yaw Multi-Pitch High-Quality Dataset and Benchmark for Facial Pose Analysis

Peipei Li, Xiang Wu, Yibo Hu, Ran He, Zhenan Sun

ICCV 2019 · 3D vision › Face and shape · approach: 3D morphable face model regression · 44 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 ours instead of CAPG-GANOurs vs CAPG-GAN · Multi-PIE Setting 2 (±90° yaw)Rank-1 accuracy (%): 66.05 -> 75.33Improved
add parsing guided local discriminator method vs TP-GANOurs vs TP-GAN · M2FPA 0° pitch ±90° yaw, LightCNN-29 v2Rank-1 accuracy (%): 62.1 -> 67.6Improved
frontalize with ours before recognition (vs original images)IR-50 · M2FPA 0° pitch ±90° yawRank-1 accuracy (%): 35.3 -> 55.8Improved
frontalize with DR-GAN before recognition (vs original images)LightCNN-29 v2 · M2FPA 0° pitch ±60° yawRank-1 accuracy (%): 98.6 -> 89.5Hurt
increase pitch angle from 0° to ±30° at ±90° yawOriginal images, LightCNN-29 v2 · M2FPARank-1 accuracy (%): 51.7 -> 24.5Hurt
frontalize with ours at small yaw (±15° to ±45°)LightCNN-29 v2 · M2FPA 0° pitchRank-1 accuracy (%): 100 -> 100No 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