mlsanityData to 7 Oct 2026

NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images

arXiv 2303.07653 ↗First posted 14 Mar 2023cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field representing the density distribution of 3D edges which we refer to as Neural Edge Field (NEF). Inspired by NeRF, NEF is optimized with a view-based rendering loss where a 2D edge map is rendered at a given view and is compared to the ground-truth edge map extracted from the image of that view. The rendering-based differentiable optimization of NEF fully exploits 2D edge detection, without needing a supervision of 3D edges, a 3D geometric operator or cross-view edge correspondence. Several technical designs are devised to ensure learning a range-limited and view-independent NEF for robust edge extraction. The final parametric 3D curves are extracted from NEF with an iterative optimization method. On our benchmark with synthetic data, we demonstrate that NEF outperforms existing state-of-the-art methods on all metrics. Project page: https://yunfan1202.github.io/NEF/.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 25 of its 45 references that are in the map. First posted on arXiv 14 Mar 2023.

Builds on

25 of 45 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  5. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  6. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  7. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  8. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  9. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  10. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  11. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  12. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
13 more
  1. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  2. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  3. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  4. 2017A General and Adaptive Robust Loss Functioncited by 236
  5. 2021Editing Conditional Radiance Fieldscited by 222
  6. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  7. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 167
  8. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  9. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  10. 2019BlenderProccited by 76
  11. 2020PIE-NET: Parametric Inference of Point Cloud Edgescited by 67
  12. 2020Neural Volume Rendering: NeRF And Beyondcited by 44
  13. 2021PC2WF: 3D Wireframe Reconstruction from Raw Point Cloudscited by 33

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 6; 2026: 6.

22 papers.

Sort:

  1. 20243Doodle: Compact Abstraction of Objects with 3D Strokescited by 21
  2. 2025Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenescited by 20
  3. 20243D Neural Edge Reconstructioncited by 12
  4. 2024EdgeGaussians -- 3D Edge Mapping via Gaussian Splattingcited by 10
  5. 2024Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Renderingcited by 9
  6. 2025Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstructioncited by 9
  7. 2024Parametric Primitive Analysis of CAD Sketches with Vision Transformercited by 7
  8. 2024Relighting Scenes with Object Insertions in Neural Radiance Fieldscited by 5
  9. 2025SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splattingcited by 5
  10. 2024MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Imagescited by 3
  11. 2025WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstractioncited by 3
  12. 2024LineGS : 3D Line Segment Representation on 3D Gaussian Splattingcited by 2
10 more
  1. 2024EDCSSM: Edge Detection with Convolutional State Space Modelcited by 1
  2. 2025Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibilitycited by 1
  3. 2026Sketch&Patch++: Efficient Structure-Aware 3D Gaussian Representationcited by 1
  4. 2024LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streamingcited by 0
  5. 2025STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Cloudscited by 0
  6. 2026RoEL: Robust Event-based 3D Line Reconstructioncited by 0
  7. 2026BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splattingcited by 0
  8. 2026Random Walk on Point Clouds for Feature Detectioncited by 0
  9. 2026One Shot Learning for Edge Detection on Point Cloudscited by 0
  10. 2026FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printingcited by 0