AI Paper Atlas

Research map / 3D vision / 3D generation

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

Jia Zheng, Junfei Zhang, Jing Li, Rui Tang, Shenghua Gao, Zihan Zhou

ECCV 2020 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 309 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 synthetic data with real data (s + r) instead of real onlyHorizonNet · PanoContext (layout estimation)3D IoU (%): 83.42 -> 84.45Improved
pre-train on synthetic then fine-tune (s -> r) instead of real onlyHorizonNet · 2D-3D-S (layout estimation)3D IoU (%): 84.33 -> 86.01Improved
pre-train on synthetic then fine-tune (s -> r) instead of real onlyLayoutNet · PanoContext (layout estimation)3D IoU (%): 84.15 -> 84.77Improved
pre-train on synthetic then fine-tune (s -> r) instead of real onlyLayoutNet · 2D-3D-S (layout estimation)3D IoU (%): 83.39 -> 84.04Improved
add synthetic data with real data via BGC (s + r) instead of real onlyLayoutNet · PanoContext (layout estimation)3D IoU (%): 84.15 -> 84.96Improved
add synthetic data with real data via BGC (s + r) instead of real onlyHorizonNet · 2D-3D-S (layout estimation)3D IoU (%): 84.33 -> 84.36No clear effect
increase synthetic pre-training images from 1k to 10k (ablation)HorizonNet · PanoContext (layout estimation)3D IoU (%): 83.77 -> 85.27Improved
increase synthetic pre-training images from 1k to 10k (ablation)LayoutNet · PanoContext (layout estimation)3D IoU (%): 83.81 -> 84.77Improved
increase synthetic pre-training images from 1k to 5k (ablation)LayoutNet · 2D-3D-S (layout estimation)3D IoU (%): 83.57 -> 84.55Improved
increase synthetic pre-training images from 5k to 10k (ablation)HorizonNet · 2D-3D-S (layout estimation)3D IoU (%): 86.35 -> 86.01Hurt
add discriminator to align layout outputs between synthetic and real domainsLayoutNet · 2D-3D-S (layout estimation)3D IoU (%): 57.18 -> 70.08Improved
add discriminator to align layout outputs between synthetic and real domainsLayoutNet · PanoContext (layout estimation)3D IoU (%): 75.64 -> 76.91Improved

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