# PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments

arXiv: https://arxiv.org/abs/2007.09584 · HTML: https://mlsanity.com/paper/2007.09584/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2020.

## Built on by (most cited first, 30 of 56)

- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [Anchor-free Oriented Proposal Generator for Object Detection](https://mlsanity.com/paper/2110.01931/) (2021)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [The KFIoU Loss for Rotated Object Detection](https://mlsanity.com/paper/2201.12558/) (2022)
- [Focal and Efficient IOU Loss for Accurate Bounding Box Regression](https://mlsanity.com/paper/2101.08158/) (2021)
- [Adaptive Rotated Convolution for Rotated Object Detection](https://mlsanity.com/paper/2303.07820/) (2023)
- [Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization](https://mlsanity.com/paper/2209.10839/) (2022)
- [H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection](https://mlsanity.com/paper/2210.06742/) (2022)
- [A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection](https://mlsanity.com/paper/2109.12848/) (2021)
- [G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection](https://mlsanity.com/paper/2205.11796/) (2022)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [Rethinking IoU-based Optimization for Single-stage 3D Object Detection](https://mlsanity.com/paper/2207.09332/) (2022)
- [Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection](https://mlsanity.com/paper/2106.06072/) (2021)
- [Rethinking Boundary Discontinuity Problem for Oriented Object Detection](https://mlsanity.com/paper/2305.10061/) (2023)
- [GRA: Detecting Oriented Objects through Group-wise Rotating and Attention](https://mlsanity.com/paper/2403.11127/) (2024)
- [FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection](https://mlsanity.com/paper/2111.10780/) (2021)
- [OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images](https://mlsanity.com/paper/2409.19648/) (2024)
- [Theoretically Achieving Continuous Representation of Oriented Bounding Boxes](https://mlsanity.com/paper/2402.18975/) (2024)
- [Oriented object detection in optical remote sensing images using deep learning: a survey](https://mlsanity.com/paper/2302.10473/) (2023)
- [DARDet: A Dense Anchor-free Rotated Object Detector in Aerial Images](https://mlsanity.com/paper/2110.01025/) (2021)
- [AlphaRotate: A Rotation Detection Benchmark using TensorFlow](https://mlsanity.com/paper/2111.06677/) (2021)
- [FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection](https://mlsanity.com/paper/2401.06159/) (2023)
- [Fewer is More: Efficient Object Detection in Large Aerial Images](https://mlsanity.com/paper/2212.13136/) (2022)
- [GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection](https://mlsanity.com/paper/2502.01565/) (2025)
- [SOAR: Advancements in Small Body Object Detection for Aerial Imagery Using State Space Models and Programmable Gradients](https://mlsanity.com/paper/2405.01699/) (2024)
- [DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detection](https://mlsanity.com/paper/2408.06123/) (2024)
- [DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection](https://mlsanity.com/paper/2109.06148/) (2021)

## Abstract (arXiv)

Object detection using an oriented bounding box (OBB) can better target rotated objects by reducing the overlap with background areas. Existing OBB approaches are mostly built on horizontal bounding box detectors by introducing an additional angle dimension optimized by a distance loss. However, as the distance loss only minimizes the angle error of the OBB and that it loosely correlates to the IoU, it is insensitive to objects with high aspect ratios. Therefore, a novel loss, Pixels-IoU (PIoU) Loss, is formulated to exploit both the angle and IoU for accurate OBB regression. The PIoU loss is derived from IoU metric with a pixel-wise form, which is simple and suitable for both horizontal and oriented bounding box. To demonstrate its effectiveness, we evaluate the PIoU loss on both anchor-based and anchor-free frameworks. The experimental results show that PIoU loss can dramatically improve the performance of OBB detectors, particularly on objects with high aspect ratios and complex backgrounds. Besides, previous evaluation datasets did not include scenarios where the objects have high aspect ratios, hence a new dataset, Retail50K, is introduced to encourage the community to adapt OBB detectors for more complex environments.