Research map / 3D vision / 3D generation
Learning to Parse Wireframes in Images of Man-Made Environments
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use the learned junction detector instead of Manhattan junction detection or a contrario junction detection | Wireframe method · Wireframe dataset test set, junction detection | precision-recall | Helped |
| Use the learned line detector instead of LSD or MCMLSD | Wireframe method · Wireframe dataset test set, line segment detection | precision-recall | Helped |
| Use the learned line detector instead of LSD or MCMLSD | Wireframe method · York Urban dataset, line segment detection | precision-recall | Helped |
| Use a Stacked Hourglass network rather than an Inception network for line detection (ablation) | Line detector · Wireframe dataset | line detection performance | Helped |
| Use length-dependent ℓ2 loss rather than cross-entropy loss for line detection (ablation) | Line detector · Wireframe dataset | line detection performance | Helped |
Closest papers by meaning
- PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds (ICLR 2021 · similarity 0.87)
- NEAT: Distilling 3D Wireframes from Neural Attraction Fields (CVPR 2024 · similarity 0.87)
- Automatic High Resolution Wire Segmentation and Removal (CVPR 2023 · similarity 0.84)
- Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB Image (CVPR 2020 · similarity 0.84)
- Im2Struct: Recovering 3D Shape Structure From a Single RGB Image (CVPR 2018 · similarity 0.84)
- EdgeDiff: Edge-aware Diffusion Network for Building Reconstruction from Point Clouds (CVPR 2025 · similarity 0.83)
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.