mlsanityData to 7 Oct 2026

3D Neural Edge Reconstruction

arXiv 2405.19295 ↗First posted 29 May 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Real-world objects and environments are predominantly composed of edge features, including straight lines and curves. Such edges are crucial elements for various applications, such as CAD modeling, surface meshing, lane mapping, etc. However, existing traditional methods only prioritize lines over curves for simplicity in geometric modeling. To this end, we introduce EMAP, a new method for learning 3D edge representations with a focus on both lines and curves. Our method implicitly encodes 3D edge distance and direction in Unsigned Distance Functions (UDF) from multi-view edge maps. On top of this neural representation, we propose an edge extraction algorithm that robustly abstracts parametric 3D edges from the inferred edge points and their directions. Comprehensive evaluations demonstrate that our method achieves better 3D edge reconstruction on multiple challenging datasets. We further show that our learned UDF field enhances neural surface reconstruction by capturing more details.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 54 of its 76 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

54 of 76 references.

References · 54

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  5. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  6. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  9. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  10. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
38 more
  1. 2020Convolutional Occupancy Networkscited by 760
  2. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  3. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  4. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  5. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  6. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  7. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  8. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  9. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  10. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  11. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  12. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  13. 2021Neural RGB-D Surface Reconstructioncited by 312
  14. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 267
  15. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  16. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  17. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 167
  18. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  19. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 120
  20. 2019Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detectioncited by 104
  21. 2020TPNet: Trajectory Proposal Network for Motion Predictioncited by 80
  22. 2022NerfAcc: A General NeRF Acceleration Toolboxcited by 73
  23. 2020PIE-NET: Parametric Inference of Point Cloud Edgescited by 67
  24. 2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 65
  25. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 62
  26. 2022DeepLSD: Line Segment Detection and Refinement with Deep Image Gradientscited by 58
  27. 2018Learning Attraction Field Representation for Robust Line Segment Detectioncited by 52
  28. 2021SOLD2: Self-supervised Occlusion-aware Line Description and Detectioncited by 45
  29. 20233D Line Mapping Revisitedcited by 39
  30. 2021RoadMap: A Light-Weight Semantic Map for Visual Localization towards Autonomous Drivingcited by 34
  31. 2021PC2WF: 3D Wireframe Reconstruction from Raw Point Cloudscited by 33
  32. 2021RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depthcited by 33
  33. 2022Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learningcited by 26
  34. 2017Robust Visual SLAM with Point and Line Featurescited by 23
  35. 2021UV-SLAM: Unconstrained Line-based SLAM Using Vanishing Points for Structural Mappingcited by 23
  36. 2023NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Imagescited by 22
  37. 2023NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloudcited by 22
  38. 2022Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Camerascited by 16

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 3.

12 papers.

  1. 2025Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenescited by 20
  2. 2024EdgeGaussians -- 3D Edge Mapping via Gaussian Splattingcited by 10
  3. 2025Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstructioncited by 9
  4. 2025SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splattingcited by 5
  5. 2025WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstractioncited by 3
  6. 2025Recovering Dynamic 3D Sketches from Videoscited by 2
  7. 2026Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representationcited by 1
  8. 2026Interacted Planes Reveal 3D Line Mappingcited by 1
  9. 2024LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streamingcited by 0
  10. 2025MRASfM: Multi-Camera Reconstruction and Aggregation through Structure-from-Motion in Driving Scenescited by 0
  11. 2025Order Matters: 3D Shape Generation from Sequential VR Sketchescited by 0
  12. 2026RoEL: Robust Event-based 3D Line Reconstructioncited by 0