AI Paper Atlas

Research map / 3D vision / Depth and stereo

Structured Outdoor Architecture Reconstruction by Exploration and Classification

Fuyang Zhang, Xiang Xu, Nelson Nauata, Yasutaka Furukawa

ICCV 2021 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 14 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
apply explore-and-classify on top of Conv-MPNConv-MPN · Aerial building reconstruction (initial Conv-MPN)edge F1: 58.1 -> 67.1Improved
apply explore-and-classify on top of Conv-MPNConv-MPN · Aerial building reconstruction (initial Conv-MPN)region F1: 54.9 -> 63.5Improved
apply explore-and-classify on top of Conv-MPNConv-MPN · Aerial building reconstruction (initial Conv-MPN)corner F1: 78.8 -> 83.2Improved
apply REPL (REINFORCE-based RL) refinement to Conv-MPNConv-MPN · Aerial building reconstruction (initial Conv-MPN)region F1: 54.9 -> 15.9Hurt
apply Lin et al. DQN-based refinement to Conv-MPNConv-MPN · Aerial building reconstruction (initial Conv-MPN)edge F1: 58.1 -> 51.6Hurt
replace beam search with Sequential Monte Carlo (ablation)explore-and-classify · Aerial building reconstruction (initial Conv-MPN, search comparison)corner F1: 83.2 -> 81.2Mixed
train classifiers on Conv-MPN instead of Per-edge reconstructions, tested on Per-edgeexplore-and-classify · Cross-initialization (test-time init Per-edge)edge F1: 57.5 -> 60.3Improved
train and test on mismatched initial reconstructions (Nauata-trained, Conv-MPN test)explore-and-classify · Cross-initialization (test-time init Conv-MPN)edge F1: 67.1 -> 67.0No clear effect
add the geometry classification module (vs heuristic confidence-map scoring) (ablation)explore-and-classify · Aerial building reconstruction (three initial reconstructions)corner/edge/region F1Improved
add classifier-guided data augmentation by exploration (vs no augmentation) (ablation)explore-and-classify · Aerial building reconstruction (Per-edge and Nauata initial)corner/edge/region F1Improved
use classifier-guided exploration instead of random sampling for training data (ablation)explore-and-classify · Aerial building reconstruction (Per-edge and Nauata initial)region F1Improved
increase search depth, no-augmentation versus exploration (ablation)explore-and-classify · Aerial building reconstructioncorner/edge/region F1Improved

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