AI Paper Atlas

Research map / 3D vision / Face and shape

A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image

Ruiqi Zhao, Yan Wang, Aleix M. Martínez

TPAMI 2017 · 3D vision › Face and shape · approach: 3D morphable face model regression · 48 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 a deep feed-forward network instead of linear shape-basis models for 2D-to-3D landmark lifting3D shape recovery from 2D landmarks · CMU Motion Capture (Subject 13)reconstruction error: .0653 -> .0229Improved
use the deep network instead of Ramakrishna et al. on Subject 153D shape recovery from 2D landmarks · CMU Motion Capture (Subject 15)reconstruction error: .0675 -> .0099Improved
use the deep network instead of Zhou et al. on BU-3DFE faces3D shape recovery from 2D landmarks · BU-3DFE Facereconstruction error: 0.0053 -> 0.0040Improved
use the deep network instead of Zhou et al. on 3DFAW3D shape recovery from 2D landmarks · 3DFAWreconstruction error: 0.0055 -> 0.0042Improved
use the deep network instead of Zhou et al. on cars3D shape recovery from 2D landmarks · FG3DCarreconstruction error: 0.0042 -> 0.0022Improved
add the recurrent layer so one randomly missing landmark is estimated jointly with depth3D shape recovery from 2D landmarks · CMU Motion Capture (Subject 13)reconstruction error: .0229 -> 0.0413Hurt
missing one landmark during training and testing on BU-3DFE faces3D shape recovery from 2D landmarks · BU-3DFE Facereconstruction error: 0.0040 -> 0.006Hurt
add Gaussian noise (about 3% of object size) to input 2D landmarks3D shape recovery from 2D landmarks · CMU Motion Capturereconstruction errorNo 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