# Learning to Reconstruct 3D Manhattan Wireframes from a Single Image

arXiv: https://arxiv.org/abs/1905.07482 · HTML: https://mlsanity.com/paper/1905.07482/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 30 of 35)

- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021)
- [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023)
- [PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models](https://mlsanity.com/paper/2306.01461/) (2023)
- [PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds](https://mlsanity.com/paper/2103.02766/) (2021)
- [HEAT: Holistic Edge Attention Transformer for Structured Reconstruction](https://mlsanity.com/paper/2111.15143/) (2021)
- [Depth Prompting for Sensor-Agnostic Depth Estimation](https://mlsanity.com/paper/2405.11867/) (2024)
- [Fully Convolutional Line Parsing](https://mlsanity.com/paper/2104.11207/) (2021)
- [ELSED: Enhanced Line SEgment Drawing](https://mlsanity.com/paper/2108.03144/) (2021)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [ELSD: Efficient Line Segment Detector and Descriptor](https://mlsanity.com/paper/2104.14205/) (2021)
- [Deep vanishing point detection: Geometric priors make dataset variations vanish](https://mlsanity.com/paper/2203.08586/) (2022)
- [Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World](https://mlsanity.com/paper/2505.04788/) (2025)
- [HoW-3D: Holistic 3D Wireframe Perception from a Single Image](https://mlsanity.com/paper/2208.06999/) (2022)
- [NEAT: Distilling 3D Wireframes from Neural Attraction Fields](https://mlsanity.com/paper/2307.10206/) (2023)
- [EdgeGaussians -- 3D Edge Mapping via Gaussian Splatting](https://mlsanity.com/paper/2409.12886/) (2024)
- [Learning to Construct 3D Building Wireframes from 3D Line Clouds](https://mlsanity.com/paper/2208.11948/) (2022)
- [Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction](https://mlsanity.com/paper/2308.10694/) (2023)
- [Generating 3D House Wireframes with Semantics](https://mlsanity.com/paper/2407.12267/) (2024)
- [CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation](https://mlsanity.com/paper/2504.19174/) (2025)
- [A Comprehensive Review of Image Line Segment Detection and Description: Taxonomies, Comparisons, and Challenges](https://mlsanity.com/paper/2305.00264/) (2023)
- [PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus](https://mlsanity.com/paper/2401.14919/) (2024)
- [3D Parametric Wireframe Extraction Based on Distance Fields](https://mlsanity.com/paper/2107.06165/) (2021)
- [LineGS : 3D Line Segment Representation on 3D Gaussian Splatting](https://mlsanity.com/paper/2412.00477/) (2024)
- [Recurrence-based Vanishing Point Detection](https://mlsanity.com/paper/2412.20666/) (2024)
- [3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience](https://mlsanity.com/paper/2604.08042/) (2026)
- [A-Scan2BIM: Assistive Scan to Building Information Modeling](https://mlsanity.com/paper/2311.18166/) (2023)
- [The Impact of Semi-Supervised Learning on Line Segment Detection](https://mlsanity.com/paper/2411.04596/) (2024)
- [Deep Polycuboid Fitting for Compact 3D Representation of Indoor Scenes](https://mlsanity.com/paper/2503.14912/) (2025)
- [Aligned Anchor Groups Guided Line Segment Detector](https://mlsanity.com/paper/2509.00786/) (2025)

## Abstract (arXiv)

In this paper, we propose a method to obtain a compact and accurate 3D wireframe representation from a single image by effectively exploiting global structural regularities. Our method trains a convolutional neural network to simultaneously detect salient junctions and straight lines, as well as predict their 3D depth and vanishing points. Compared with the state-of-the-art learning-based wireframe detection methods, our network is simpler and more unified, leading to better 2D wireframe detection. With global structural priors from parallelism, our method further reconstructs a full 3D wireframe model, a compact vector representation suitable for a variety of high-level vision tasks such as AR and CAD. We conduct extensive evaluations on a large synthetic dataset of urban scenes as well as real images. Our code and datasets have been made public at https://github.com/zhou13/shapeunity.