AI Paper Atlas

Research map / 3D vision / 3D generation

Convex Decomposition of Indoor Scenes

Vaibhav Vavilala, David Forsyth

ICCV 2023 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 6 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
initialize refinement with network prediction instead of random start (ablation)convex decomposition refinement · NYUv2 testAbsRel: 0.447 -> 0.163Improved
add refinement (polishing) after the network prediction (ablation)network-only decomposition · NYUv2 testAbsRel: 0.179 -> 0.163Improved
add backward-selection pruning during refinement (ablation)refinement · NYUv2 test, non-oracleAbsRel: 0.166 -> 0.144 (n_used 24.0 -> 14.4)Improved
use GT depth in refinement instead of inferred depth (ablation)refinement · NYUv2 testAbsRel: 0.144 -> 0.098Improved
use GT segmentation instead of inferred segmentation in refinement (ablation)refinement · NYUv2 testAbsRel: 0.098 -> 0.098No clear effect
add entropy segmentation loss (ablation)convex decomposition · NYUv2 testSeg accuracy: 0.629 -> 0.615No clear effect
add Manhattan world losses (ablation)convex decomposition · NYUv2 test, non-oracleAbsRel: 0.189 -> 0.144Improved
split each convex into 8 pieces before refinement (ablation)refinement · NYUv2 test, non-oracleAbsRel / Seg accuracy: AbsRel 0.144 -> 0.183; Seg_Acc 0.615 -> 0.630Mixed
increase initial convex count beyond 24 (36, 48, 60) (ablation)convex decomposition · NYUv2 test, non-oracleAbsRel: 0.144 -> 0.198 (36)Hurt
reduce initial convex count to 12 (ablation)convex decomposition · NYUv2 test, non-oracleAbsRel: 0.144 -> 0.185Hurt
add volume ordering loss (ablation)convex decomposition · NYUv2 test, non-oracleAbsRel: 0.144 -> 0.144No clear effect
keep localization loss (ablation)convex decomposition · NYUv2 test, non-oracleAbsRel: 0.499 -> 0.144Improved

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