mlsanityData to 7 Oct 2026

Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances

arXiv 2502.04268 ↗First posted 6 Feb 2025cs.CV cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

With the rapidly increasing demand for oriented object detection (OOD), recent research involving weakly-supervised detectors for learning OOD from point annotations has gained great attention. In this paper, we rethink this challenging task setting with the layout among instances and present Point2RBox-v2. At the core are three principles: 1) Gaussian overlap loss. It learns an upper bound for each instance by treating objects as 2D Gaussian distributions and minimizing their overlap. 2) Voronoi watershed loss. It learns a lower bound for each instance through watershed on Voronoi tessellation. 3) Consistency loss. It learns the size/rotation variation between two output sets with respect to an input image and its augmented view. Supplemented by a few devised techniques, e.g. edge loss and copy-paste, the detector is further enhanced. To our best knowledge, Point2RBox-v2 is the first approach to explore the spatial layout among instances for learning point-supervised OOD. Our solution is elegant and lightweight, yet it is expected to give a competitive performance especially in densely packed scenes: 62.61%/86.15%/34.71% on DOTA/HRSC/FAIR1M. Code is available at https://github.com/VisionXLab/point2rbox-v2.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 55 of its 77 references that are in the map. First posted on arXiv 6 Feb 2025.

Builds on

55 of 77 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023Segment Anythingcited by 8,158
  4. 2017Mask R-CNNcited by 7,259
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  8. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  9. 2018Object Detection with Deep Learning: A Reviewcited by 524
  10. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  11. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 339
  12. 2019Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challengescited by 313
38 more
  1. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  2. 2017EAST: An Efficient and Accurate Scene Text Detectorcited by 248
  3. 2021Oriented R-CNN for Object Detectioncited by 230
  4. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  5. 2019R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Objectcited by 193
  6. 2020Align Deep Features for Oriented Object Detectioncited by 186
  7. 2021Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Losscited by 156
  8. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 150
  9. 2021FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagerycited by 143
  10. 2021Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergencecited by 130
  11. 2022MMRotate: A Rotated Object Detection Benchmark using PyTorchcited by 115
  12. 2018FOTS: Fast Oriented Text Spotting with a Unified Networkcited by 109
  13. 2021Anchor-free Oriented Proposal Generator for Object Detectioncited by 104
  14. 2021Oriented RepPoints for Aerial Object Detectioncited by 102
  15. 2018Rotation-Sensitive Regression for Oriented Scene Text Detectioncited by 88
  16. 2020Dense Label Encoding for Boundary Discontinuity Free Rotation Detectioncited by 79
  17. 2019Learning Modulated Loss for Rotated Object Detectioncited by 73
  18. 2022The KFIoU Loss for Rotated Object Detectioncited by 73
  19. 2020Dynamic Refinement Network for Oriented and Densely Packed Object Detectioncited by 72
  20. 2019Precise Detection in Densely Packed Scenescited by 62
  21. 2020SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothingcited by 62
  22. 2018Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networkscited by 54
  23. 2022Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detectioncited by 43
  24. 2022Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalizationcited by 36
  25. 2022H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detectioncited by 36
  26. 2020On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisitedcited by 32
  27. 2022Point-to-Box Network for Accurate Object Detection via Single Point Supervisioncited by 31
  28. 2024STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagerycited by 31
  29. 2023H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detectioncited by 28
  30. 2023Tiny and Efficient Model for the Edge Detection Generalizationcited by 28
  31. 2022Weakly-Supervised Salient Object Detection Using Point Supervisioncited by 25
  32. 2023PointOBB: Learning Oriented Object Detection via Single Point Supervisioncited by 25
  33. 2024PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Imagescited by 24
  34. 2023Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transportcited by 23
  35. 2023Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervisioncited by 21
  36. 2022G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detectioncited by 20
  37. 2021Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detectioncited by 17
  38. 2024PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detectioncited by 13

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 7.

11 papers.

  1. 2025Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detectioncited by 6
  2. 2025Partial Weakly-Supervised Oriented Object Detectioncited by 3
  3. 2025Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilizationcited by 2
  4. 2026Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Imagescited by 1
  5. 2025Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detectioncited by 0
  6. 2026SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detectioncited by 0
  7. 2026SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awarenesscited by 0
  8. 2026Diffuse to Detect: Bi-Level Sample Rebalancing with Pseudo-Label Diffusion for Point-Supervised Infrared Small-Target Detectioncited by 0
  9. 2026SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detectioncited by 0
  10. 2026PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Trackingcited by 0
  11. 2026Geometry Meets Semantics: Fractional Gradient Stabilization for Semantic-Driven Bounding Box Optimization in Visual Detection Taskscited by 0