AI Paper Atlas

Research map / 3D vision / Depth and stereo

Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery

Lei Jin, Yanyu Xu, Jia Zheng, Junfei Zhang, Rui Tang, Shugong Xu, Jingyi Yu, Shenghua Gao

CVPR 2020 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 80 citations (OpenAlex)

Check 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 corner, boundary, and plane structure as both prior and regularizer (ablation)Ours-baseline depth estimation · Stanford 2D-3D-SRMS: 0.472 -> 0.421Improved
add corner information (ablation)Geometric structure based depth estimation · Stanford 2D-3D-SRMS: 0.425 -> 0.421Improved
add boundary information (ablation)Geometric structure based depth estimation · Stanford 2D-3D-SRMS: 0.436 -> 0.421Improved
add plane information (ablation)Geometric structure based depth estimation · Stanford 2D-3D-SRMS: 0.429 -> 0.421Improved
add structure as a prior (ablation)Depth estimation with geometric structure regularizer · Stanford 2D-3D-SRMS: 0.448 -> 0.421Improved
add structure as a regularizer (ablation)Depth estimation with geometric structure prior · Stanford 2D-3D-SRMS: 0.446 -> 0.421Improved
add geometric structure information (ablation)Depth estimation on synthetic rooms without furniture · Synthetic dataset, without furnitureRMS: 0.668 -> 0.642Improved
add geometric structure information (ablation)Depth estimation on synthetic rooms with furniture · Synthetic dataset, with furnitureRMS: 0.721 -> 0.666Improved
add the attention module (ablation)Depth estimation trained with furniture and tested without furniture · Synthetic dataset, without furnitureRMS: 0.784 -> 0.730Improved
add geometric structure prior, furniture attention, and structure regularizationDepth estimation on Stanford 2D-3D-S · Stanford 2D-3D-SRMS[m]: 0.472 -> 0.421Improved
use the proposed geometric representation for counterfactual depthCounterfactual depth estimation · Counterfactual depthRMS: 0.845 -> 0.823Improved

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