Lune

CVPR2025Top-tier venue

GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection

Jose Henrique Lima Marques, Jeffri Murrugarra-Llerena, Cláudio R. Jung

Abstract

Oriented Object Detection (OOD) has received increased attention in the past years, being a suitable solution for detecting elongated objects in remote sensing analysis. In particular, using regression loss functions based on Gaussian distributions has become attractive since they yield simple and differentiable terms. However, existing solutions are still based on regression heads that produce Oriented Bounding Boxes (OBBs), and the known problem of angular boundary discontinuity persists. In this work, we propose a regression head for OOD that directly produces Gaussian distributions based on the Cholesky matrix decomposition. The proposed head, named GauCho, theoretically mitigates the boundary discontinuity problem and is fully compatible with recent Gaussian-based regression loss functions. Furthermore, we advocate using Oriented Ellipses (OEs) to represent oriented objects, which relates to GauCho through a bijective function and alleviates the encoding ambiguity problem for circular objects. Our experimental results show that GauCho can be a viable alternative to the traditional OBB head, achieving results comparable to or better than state-of-the-art detectors for the challenging dataset DOTA. Our code will be available at https://github.com/jhlmarques/GauCho.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
  • Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence cites FCOS: Fully Convolutional One-Stage Object Detection
  • Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence cites Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
  • Oriented RepPoints for Aerial Object Detection cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
  • Oriented RepPoints for Aerial Object Detection cites FCOS: Fully Convolutional One-Stage Object Detection
  • Oriented RepPoints for Aerial Object Detection cites Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
  • Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on15

  1. FCOS: Fully Convolutional One-Stage Object DetectionZhi Tian, Chunhua Shen, Hao Chen, Tong HeICCV 2019 · 6,042 citations
  2. SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated ObjectsXue Yang, Jirui Yang, Junchi Yan, Yue Zhang et al.ICCV 2019 · 865 citations
  3. Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler DivergenceXue Yang, Xiaojiang Yang, Jirui Yang, Qi Ming et al.NeurIPS 2021 · 603 citations
  4. Rethinking Rotated Object Detection with Gaussian Wasserstein Distance LossXue Yang, Junchi Yan, Qi Ming, Wentao Wang et al.ICML 2021 · 572 citations
  5. Oriented RepPoints for Aerial Object DetectionWentong Li, Yijie Chen, Kaixuan Hu, Jianke ZhuCVPR 2022 · 487 citations

Related papers

  1. Theoretically Achieving Continuous Representation of Oriented Bounding BoxesZi-Kai Xiao, Guo-Ye Yang, Xue Yang, Tai-Jiang Mu et al.CVPR 2024 · 20 citations
  2. Rethinking Boundary Discontinuity Problem for Oriented Object DetectionHang Xu, Xinyuan Liu, Haonan Xu, Yike Ma et al.CVPR 2024 · 30 citations
  3. SPWOOD: Sparse Partial Weakly-Supervised Oriented Object DetectionWei Zhang, Xiang Liu, Ningjing Liu, Mingxin Liu et al.ICLR 2026
  4. Dynamic Anchor Learning for Arbitrary-Oriented Object DetectionQi Ming, Zhiqiang Zhou, Lingjuan Miao, Hongwei Zhang et al.AAAI 2021 · 332 citations
  5. Partial Weakly-Supervised Oriented Object DetectionMingxin Liu, Peiyuan Zhang, Yuan Liu, Wei Zhang et al.CVPR 2026 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines