AI Paper Atlas

Research map / 3D vision / 3D generation

Volumetric performance capture from minimal camera viewpoints

Andrew Gilbert, Marco Volino, John Collomosse, Adrian Hilton

ECCV 2018 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 52 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
apply the autoencoder to a 2-camera PVHprobabilistic visual hull · TotalCapture, 2 camerasMSE x 1e-3: 24.6 -> 7.71Improved
apply the autoencoder to a 4-camera PVHprobabilistic visual hull · TotalCapture, 4 camerasMSE x 1e-3: 11.6 -> 7.60Improved
use overlapping patches (overlap 16) instead of no overlap (32) (ablation)autoencoder, 2 cameras · TotalCapture 32^3 patchesMSE x 1e-3: 9.20 -> 7.71Improved
use overlapping patches (overlap 8) instead of no overlap (32) (ablation)autoencoder, 4 cameras · TotalCapture 32^3 patchesMSE x 1e-3: 8.28 -> 7.33Improved
reduce patch overlap from 8 to 16 (ablation)autoencoder, 2 cameras · TotalCapture 32^3 patchesMSE x 1e-3: 7.75 -> 7.71No clear effect
process the whole 64^3 volume instead of 32^3 patches with overlap 8 (ablation)autoencoder, 2 cameras · TotalCapture 64^3 PVHMSE x 1e-3: 6.10 -> 6.00No clear effect
remove patch overlap for 32^3 patches (overlap 32 vs 8) (ablation)autoencoder, 2 cameras · TotalCapture 64^3 PVHMSE x 1e-3: 7.20 -> 6.10Improved
use 4 cameras in 180 degree arc instead of 2 neighbouring camerasautoencoder · TotalCaptureMSE x 1e-3: 7.71 -> 7.60Improved
transfer the TotalCapture model to Human3.6M without retrainingautoencoder, 2 cameras · Human3.6MMSE x 1e-3: 17.4 -> 12.3Improved
use the 2-view enhanced PVH instead of an 8-view PVH for 4D reconstructionCasas et al. pipeline · 4D reconstructionPSNR: 35.1 -> 34.9No clear effect
use the 2-view enhanced PVH instead of an 8-view PVH for 4D reconstructionCasas et al. pipeline · 4D reconstructionSSIM: 0.898 -> 0.899No clear effect
use the 2-view enhanced PVH instead of an 8-view PVH (user preference)Casas et al. pipeline · AMT perceptual studypreference (%): 49.2 -> 50.7No 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