AI Paper Atlas

Research map / 3D vision / 3D generation

Large Scale Urban Scene Modeling from MVS Meshes

Lingjie Zhu, Shuhan Shen, Xiang Gao, Zhanyi Hu

ECCV 2018 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 40 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 LOD2 roof-plane extrusion instead of LOD1 averaged-height extrusionOurs · Pix4D house modelingRMS Hausdorff distance: 2.25 -> 0.21Improved
use LOD2 model instead of VSAOurs LOD2 · Pix4D house modelingnumber of triangle faces: 830 -> 24Improved
use LOD2 model instead of QEMOurs LOD2 · Pix4D house modelingRMS Hausdorff distance: 0.14 -> 0.21Hurt
use LOD2 model instead of PolyFitOurs LOD2 · Pix4D house modelingRMS Hausdorff distance: 1.27 -> 0.21Improved
use LOD2 model instead of Verdie et al.Ours LOD2 · Pix4D house modelingRMS Hausdorff distance: 1.16 -> 0.21Improved
scale from a single block to a city districtOurs · Running timesegmentation time: 25s -> 22minMixed

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