# NEAT: Distilling 3D Wireframes from Neural Attraction Fields arXiv: https://arxiv.org/abs/2307.10206 ยท HTML: https://mlsanity.com/paper/2307.10206/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 29 of its 52 references that are in the map. - First posted on arXiv 14 Jul 2023. ## Builds on (most cited first, 29 of 29) - [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017) - [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019) - [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021) - [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021) - [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022) - [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019) - [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022) - [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018) - [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021) - [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022) - [Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation](https://mlsanity.com/paper/2203.15224/) (2022) - [Object-Compositional Neural Implicit Surfaces](https://mlsanity.com/paper/2207.09686/) (2022) - [End-to-End Wireframe Parsing](https://mlsanity.com/paper/1905.03246/) (2019) - [DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images](https://mlsanity.com/paper/2208.07227/) (2022) - [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023) - [Holistically-Attracted Wireframe Parsing](https://mlsanity.com/paper/2003.01663/) (2020) - [DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients](https://mlsanity.com/paper/2212.07766/) (2022) - [Learning Attraction Field Representation for Robust Line Segment Detection](https://mlsanity.com/paper/1812.02122/) (2018) - [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021) - [A Level Set Theory for Neural Implicit Evolution under Explicit Flows](https://mlsanity.com/paper/2204.07159/) (2022) - [nerf2nerf: Pairwise Registration of Neural Radiance Fields](https://mlsanity.com/paper/2211.01600/) (2022) - [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023) - [Learning to Reconstruct 3D Manhattan Wireframes from a Single Image](https://mlsanity.com/paper/1905.07482/) (2019) - [PlaneTR: Structure-Guided Transformers for 3D Plane Recovery](https://mlsanity.com/paper/2107.13108/) (2021) - [Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning](https://mlsanity.com/paper/2210.12971/) (2022) - [NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction](https://mlsanity.com/paper/2211.16799/) (2022) - [Learning Regional Attraction for Line Segment Detection](https://mlsanity.com/paper/1912.09344/) (2019) - [HoW-3D: Holistic 3D Wireframe Perception from a Single Image](https://mlsanity.com/paper/2208.06999/) (2022) - [Level-S2fM: Structure from Motion on Neural Level Set of Implicit Surfaces](https://mlsanity.com/paper/2211.12018/) (2022) ## Built on by (most cited first, 12 of 12) - [Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes](https://mlsanity.com/paper/2501.13045/) (2025) - [PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes](https://mlsanity.com/paper/2412.03451/) (2024) - [EdgeGaussians -- 3D Edge Mapping via Gaussian Splatting](https://mlsanity.com/paper/2409.12886/) (2024) - [Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction](https://mlsanity.com/paper/2506.21401/) (2025) - [CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation](https://mlsanity.com/paper/2504.19174/) (2025) - [SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splatting](https://mlsanity.com/paper/2503.14786/) (2025) - [ScaleLSD: Scalable Deep Line Segment Detection Streamlined](https://mlsanity.com/paper/2506.09369/) (2025) - [LineGS : 3D Line Segment Representation on 3D Gaussian Splatting](https://mlsanity.com/paper/2412.00477/) (2024) - [Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representation](https://mlsanity.com/paper/2601.05394/) (2026) - [Interacted Planes Reveal 3D Line Mapping](https://mlsanity.com/paper/2602.01296/) (2026) - [LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming](https://mlsanity.com/paper/2408.14823/) (2024) - [CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction](https://mlsanity.com/paper/2609.14521/) (2026) ## Abstract (arXiv) This paper studies the problem of structured 3D reconstruction using wireframes that consist of line segments and junctions, focusing on the computation of structured boundary geometries of scenes. Instead of leveraging matching-based solutions from 2D wireframes (or line segments) for 3D wireframe reconstruction as done in prior arts, we present NEAT, a rendering-distilling formulation using neural fields to represent 3D line segments with 2D observations, and bipartite matching for perceiving and distilling of a sparse set of 3D global junctions. The proposed NEAT enjoys the joint optimization of the neural fields and the global junctions from scratch, using view-dependent 2D observations without precomputed cross-view feature matching. Comprehensive experiments on the DTU and BlendedMVS datasets demonstrate our NEAT's superiority over state-of-the-art alternatives for 3D wireframe reconstruction. Moreover, the distilled 3D global junctions by NEAT, are a better initialization than SfM points, for the recently-emerged 3D Gaussian Splatting for high-fidelity novel view synthesis using about 20 times fewer initial 3D points. Project page: urlhttps://xuenan.net/neat.