AI Paper Atlas

Research map / 3D vision / Face and shape

Shape Reconstruction Using Volume Sweeping and Learned Photoconsistency

Vincent Leroy, Jean-Sebastien Franco, Edmond Boyer

ECCV 2018 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 53 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 volumetric receptive field instead of a planar one (ablation)CNN photoconsistency classifier · DTU surface detection, 5 camerasclassifier accuracy (%): 80.67 -> 82.95Improved
use a volumetric receptive field instead of a planar one (ablation)CNN photoconsistency classifier · DTU surface detection, 20 camerasclassifier accuracy (%): 77.87 -> 84.84Improved
use a volumetric receptive field instead of a planar one (ablation)CNN photoconsistency classifier · DTU surface detection, 49 camerasclassifier accuracy (%): 75.92 -> 83.45Improved
use a learned CNN classifier instead of ZNCC (ablation)volumetric photoconsistency · DTU surface detection, 5 camerasclassifier accuracy (%): 64.98 -> 82.95Improved
use a learned CNN classifier instead of ZNCC (ablation)volumetric photoconsistency · DTU surface detection, 49 camerasclassifier accuracy (%): 65.58 -> 83.45Improved
add more cameras (5 to 49) to the planar classifier (ablation)planar CNN · DTU surface detectionclassifier accuracy (%): 80.67 -> 75.92Hurt
add more cameras (5 to 49) to the volumetric classifier (ablation)volumetric CNN · DTU surface detectionclassifier accuracy (%): 82.95 -> 83.45No clear effect
replace average pooling of pairwise features with max-pooling (ablation)multi-view network · DTUclassifier qualityNo clear effect
fuse depth maps from all views instead of single depth mapvolume sweeping · DTUmedian completeness (mm): 0.387 -> 0.296Improved
fuse depth maps from all views instead of single depth mapvolume sweeping · DTUmean completeness (mm): 1.037 -> 0.532Improved
volumetric network versus planar patch network of Hartmann et al. (single depth map)learned photoconsistency · DTUmean accuracy (mm): 1.563 -> 0.599Improved
volume sweeping versus SurfaceNetlearned MVS · DTUmean completeness (mm): 0.892 -> 0.532Improved

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