AI Paper Atlas

Research map / 3D vision / 3D generation

Learning 3D Scene Analogies with Neural Contextual Scene Maps

Junho Kim, Gwangtak Bae, Eun Sun Lee, Young Min Kim

ICCV 2025 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 1 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
add local displacement estimation after affine map (ablation)neural contextual scene maps · 3D-FRONT (avg of manual and procedural pairs)Bijectivity PCP@0.25: 0.83 -> 0.90Improved
add local displacement estimation after affine map (ablation)neural contextual scene maps · 3D-FRONT (avg of manual and procedural pairs)Chamfer Acc.@0.15: 0.77 -> 0.94Improved
add semantic embedding to descriptor field (ablation)neural contextual scene maps · 3D-FRONT manual pairs (embedding ablation)Bijectivity PCP@0.25: 0.50 -> 0.70Improved
add distance embedding to descriptor field (ablation)neural contextual scene maps · 3D-FRONT manual pairs (embedding ablation)Bijectivity PCP@0.25: 0.67 -> 0.70Improved
use CLIP embedding instead of semantic label embedding (ablation)neural contextual scene maps · 3D-FRONT (avg of manual and procedural pairs)Bijectivity PCP@0.25: 0.90 -> 0.77Mixed
use sentence embedding instead of semantic label embedding (ablation)neural contextual scene maps · 3D-FRONT (avg of manual and procedural pairs)Chamfer Acc.@0.20: 0.96 -> 0.97No clear effect
use learned descriptor fields instead of Vector Neuron 3D point featurescoarse-to-fine map estimation · 3D-FRONT procedural pairsPCP@0.25: 0.56 -> 0.76Improved
use learned descriptor fields instead of DINOv2 visual featurescoarse-to-fine map estimation · 3D-FRONT manual pairsBijectivity PCP@0.25: 0.56 -> 0.70Improved
use MAE instead of DeiT III features in visual feature field baselineVisual Feature Field · 3D-FRONT manual pairsBijectivity PCP@0.25: 0.31 -> 0.50Improved
increase RoI points sampled per object from 50 to 400neural contextual scene maps · 3D-FRONT procedural pairsPCP@0.25: 0.68 -> 0.76Improved
different instead of identical object group cardinalityneural contextual scene maps · 3D-FRONT manual pairsChamfer Acc.@0.15: 0.76 -> 0.66Hurt
our method versus 3D point feature field in sim-to-real pairsneural contextual scene maps · Sim2Real manual pairs (102 pairs)Chamfer Acc.@0.15: 0.55 -> 0.66Improved

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