mlsanityData to 7 Oct 2026

Fast Interactive Object Annotation with Curve-GCN

arXiv 1903.06874 ↗First posted 16 Mar 2019cs.CV cs.LGcited by 95

Not on the map. Why?

Abstract (arXiv)

Manually labeling objects by tracing their boundaries is a laborious process. In Polygon-RNN++ the authors proposed Polygon-RNN that produces polygonal annotations in a recurrent manner using a CNN-RNN architecture, allowing interactive correction via humans-in-the-loop. We propose a new framework that alleviates the sequential nature of Polygon-RNN, by predicting all vertices simultaneously using a Graph Convolutional Network (GCN). Our model is trained end-to-end. It supports object annotation by either polygons or splines, facilitating labeling efficiency for both line-based and curved objects. We show that Curve-GCN outperforms all existing approaches in automatic mode, including the powerful PSP-DeepLab and is significantly more efficient in interactive mode than Polygon-RNN++. Our model runs at 29.3ms in automatic, and 2.6ms in interactive mode, making it 10x and 100x faster than Polygon-RNN++.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 21; 2023: 17; 2024: 8; 2025: 12; 2026: 9.

95 papers.

Sort:

By area:

  1. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  2. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  3. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 311
  4. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  5. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 192
  6. 2023DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Modelscited by 162
  7. 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
  8. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  9. 2022EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relationscited by 139
  10. 2022BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotationscited by 99
  11. 2023Adaptive Shells for Efficient Neural Radiance Field Renderingcited by 69
  12. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
38 more
  1. 2021Adaptive Boundary Proposal Network for Arbitrary Shape Text Detectioncited by 47
  2. 2021Auto4D: Learning to Label 4D Objects from Sequential Point Cloudscited by 42
  3. 2021PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Imagescited by 42
  4. 2022PseudoClick: Interactive Image Segmentation with Click Imitationcited by 42
  5. 2022Arbitrary Shape Text Detection via Boundary Transformercited by 28
  6. 2022E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentationcited by 27
  7. 2022Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysiscited by 25
  8. 2024DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimationcited by 24
  9. 2023InterFormer: Real-time Interactive Image Segmentationcited by 20
  10. 2023Sign Language Translation with Iterative Prototypecited by 20
  11. 2023Learning the What and How of Annotation in Video Object Segmentationcited by 19
  12. 2022DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentationcited by 18
  13. 2022Interactive Multi-Class Tiny-Object Detectioncited by 14
  14. 2023Interactive Segmentation as Gaussian Process Classificationcited by 14
  15. 2021Probabilistic Attention for Interactive Segmentationcited by 12
  16. 2022SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentationcited by 12
  17. 2023BoxSnake: Polygonal Instance Segmentation with Box Supervisioncited by 12
  18. 2022BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extractioncited by 11
  19. 2024Continual Learning on Graphs: A Surveycited by 11
  20. 2025GAMED-Snake: Gradient-aware Adaptive Momentum Evolution Deep Snake Model for Multi-organ Segmentationcited by 10
  21. 2021Scaling up instance annotation via label propagationcited by 9
  22. 2023Recurrent Generic Contour-based Instance Segmentation with Progressive Learningcited by 9
  23. 2023PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenescited by 9
  24. 2021VideoClick: Video Object Segmentation with a Single Clickcited by 8
  25. 2021Robust Interactive Semantic Segmentation of Pathology Images with Minimal User Inputcited by 8
  26. 2025Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Reviewcited by 8
  27. 2021Binary segmentation of medical images using implicit spline representations and deep learningcited by 7
  28. 2021RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenescited by 7
  29. 2024Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagerycited by 7
  30. 2021LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervisioncited by 6
  31. 2023HiT: Building Mapping with Hierarchical Transformerscited by 6
  32. 2024RoIPoly: Vectorized Building Outline Extraction Using Vertex and Logit Embeddingscited by 6
  33. 2021YOLinO: Generic Single Shot Polyline Detection in Real Timecited by 4
  34. 2021BezierSeg: Parametric Shape Representation for Fast Object Segmentation in Medical Imagescited by 4
  35. 2022Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approachescited by 4
  36. 2025Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesiscited by 4
  37. 2025HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagerycited by 4
  38. 2021Weakly Supervised Volumetric Image Segmentation with Deformed Templatescited by 3

50 most cited of 95 All 95 (JSON)