AI Paper Atlas

Research map / 3D vision / Face and shape

Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-Resolution Model for Multi-Class Volumetric Labeling

CVPR 2016 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 91 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 adaptive octree refinement instead of a fixed voxel gridSemantic 3D reconstruction · Scene 1 and Scene 2overall accuracy: 92.3 -> 92.8; 83.4 -> 83.9No clear effect
Use adaptive octree refinement instead of a fixed voxel gridSemantic 3D reconstruction · Scenes 1–4, 0.4 mruntime: 430545 -> 19883; 416771 -> 19672; 91982 -> 5488; 92893 -> 4984Helped
Use adaptive octree refinement instead of a fixed voxel gridSemantic 3D reconstruction · Scenes 1–4, 0.4 mmemory: 54.3 -> 2.7; 54.3 -> 2.6; 13.6 -> 0.7; 13.6 -> 0.7Helped
Use adaptive octree refinement instead of a fixed voxel gridSemantic 3D reconstruction · Scenes 3 and 4, 0.2 mmemory: 108.5 -> 3.3; 108.5 -> 2.7Helped
Use class-specific geometric priors rather than generic surface-area regularization3D surface reconstruction · Enschede scenes3D surface shape qualityHelped

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