AI Paper Atlas

Research map / 3D vision / Face and shape

Topologically Consistent Multi-View Face Inference Using Volumetric Sampling

Tianye Li, Shichen Liu, Timo Bolkart, Jiayi Liu, Hao Li, Yajie Zhao

ICCV 2021 · 3D vision › Face and shape · approach: 3D morphable face model regression · 22 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 volumetric ToFu instead of 3DMM regression (with post-processing)multi-view face mesh inference · Light Stage multi-view face test setmedian scan-to-mesh distance (mm): 1.659 -> 0.585Improved
use volumetric ToFu instead of 3DMM regression (with post-processing)multi-view face mesh inference · Light Stage multi-view face test setmedian vertex-to-vertex distance (mm): 2.88 -> 1.97Improved
use ToFu instead of DFNRMVSmulti-view face mesh inference · Light Stage multi-view face test setmedian vertex-to-vertex distance (mm): 4.565 -> 1.973Improved
use ToFu instead of 3DMM regressionmulti-view face mesh inference · Light Stage multi-view face test setvertices below 1 mm scan-to-mesh (%): 33.1 -> 78.3Improved
use ToFu instead of 3DMM regressionmulti-view face mesh inference · Light Stage multi-view face test setmedian landmark error (mm): 3.21 -> 2.02Improved
use ToFu instead of DFNRMVS for speedmulti-view face mesh inference · Base mesh, 15 viewsruntime (s): 4.5 -> 0.385Improved
use ToFu instead of traditional MVS plus registration pipelinemulti-view face mesh inference · Base mesh, 15 viewsruntime (s): 600+ -> 0.385Improved
use mesh-based correspondence instead of optical flow2D correspondence warping · Image 1366x1003runtime (s): 30 -> 1Improved
add normal displacement weights to the mesh upsampling function (ablation)ToFu upsampling operator · Light Stage test setshape detail qualityImproved
reduce the number of input camera views (ablation)ToFu · Light Stage test setscan-to-mesh errorHurt
add successive local refinement stages after the global stage (ablation)ToFu · Light Stage test setscan-to-mesh distanceImproved

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