AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Out-of-Core Surface Reconstruction via Global TGV Minimization

Nikolai Poliarnyi

ICCV 2021 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 12 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 out-of-core GPU TGV minimization instead of in-core GDMROurs vs GDMR · Citywallpeak RAM: 75 GB -> 13.17 GBImproved
use out-of-core GPU TGV minimization instead of in-core GDMROurs vs GDMR · Citywallprocessing time: 19 h -> 63 minImproved
use out-of-core GPU TGV minimization instead of in-core GDMROurs vs GDMR · Breisachpeak RAM: 64 GB -> 10.07 GBImproved
use out-of-core GPU TGV minimization instead of in-core GDMROurs vs GDMR · Breisachprocessing time: 76 h -> 260 minImproved
use GPU-accelerated out-of-core method instead of out-of-core SSROurs vs SSR 128K · Citywallprocessing time: 58 h -> 63 minImproved
use GPU-accelerated out-of-core method instead of out-of-core SSROurs vs SSR 128K · Citywallpeak RAM: 32*8.9 GB -> 13.17 GBImproved
compare reconstruction quality with in-core GDMR on same depth mapsOurs vs GDMR · Citywall and Breisachvisual qualityNo clear effect
use delta=6 r and eta=18 r near-surface widths (smaller or larger values) (ablation)Ours · scale-diverse scenessurface qualityMixed

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