AI Paper Atlas

Research map / 3D vision / 3D generation

Scene Synthesis via Uncertainty-Driven Attribute Synchronization

Haitao Yang, Zaiwei Zhang, Siming Yan, Haibin Huang, Chongyang Ma, Yi Zheng, Chandrajit Bajaj, Qixing Huang

ICCV 2021 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 41 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 relative-attribute synchronization and prior distributions (full Sync2Gen) versus raw predicted object attributes (ablation)Sync2Gen · 3D-FRONT / SUNCG scenesscene plausibilityImproved
add relative attributes to scene optimization (prior only vs full) (ablation)Sync2Gen · 3D-FRONT bedroomrelative position qualityImproved
use Bayesian scene optimization with relative attributes and priors instead of off-the-shelf scene optimization (ablation)Sync2Gen · scene arrangementqualitative layoutImproved
compare against GRAINS baseline in living roomsSync2Gen · 3DF-living perceptual study% judged more plausible: 89.2Improved
compare against ground-truth training scenesSync2Gen · 3DF-bed perceptual study% judged more plausible: 49.7No clear effect

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