AI Paper Atlas

Research map / 3D vision / Face and shape

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction

Xiangyu Zhu, Fan Yang, Di Huang, Chang Yu, Hao Wang, Jianzhu Guo, Zhen Lei, Stan Z. Li

ECCV 2020 · 3D vision › Face and shape · approach: 3D morphable face model regression · 35 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 PNCC to the image input (ablation)FGNet-CV · FG3D-testNME (%): 3.37 -> 3.23Improved
add UV-visibility to UV-texture input (ablation)FGNet-MV · FG3D-testNME (%): 3.27 -> 3.19Improved
add UV-shape to UV-texture and UV-visibility (ablation)FGNet-MV · FG3D-testNME (%): 3.19 -> 3.10Improved
warp the image to UV space (model view) instead of camera viewFGNet · FG3D-testNME (%): 3.23 -> 3.10Improved
apply FGNet-MV to initial 3DMM fit3DDFA initial shape · FG3D-testNME (%): 5.07 -> 3.10Improved
apply FGNet-MV, error parallel to viewing direction3DDFA initial shape · FG3D-testNME (%): 3.11 -> 1.59Improved
apply FGNet-MV, error orthogonal to viewing direction3DDFA initial shape · FG3D-testNME (%): 3.44 -> 2.38Improved
use FGNet-MV versus Deng et al. cross-datasetDeng et al. · FlorenceNME (%): 6.12 -> 5.56Improved

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