lilanxiao/Rotated_IoU
A PyTorch library with CUDA extensions for computing differentiable IoU and loss functions on oriented bounding boxes in 2D and 3D.
Not currently ranked — collecting fresh signals.
star history
This repository provides CUDA-accelerated functions to calculate the intersection area of rotated rectangles using PyTorch, enabling backpropagation through IoU computation. It implements GIoU and DIoU loss variants for oriented bounding boxes in both 2D and 3D spaces. The library includes a training demo that generates synthetic box data and validates the gradients for object detection loss functions.
Frequently asked
- What is lilanxiao/Rotated_IoU?
- A PyTorch library with CUDA extensions for computing differentiable IoU and loss functions on oriented bounding boxes in 2D and 3D.
- Is Rotated_IoU open source?
- Yes — lilanxiao/Rotated_IoU is open source, released under the MIT license.
- What language is Rotated_IoU written in?
- lilanxiao/Rotated_IoU is primarily written in Python.
- How popular is Rotated_IoU?
- lilanxiao/Rotated_IoU has 443 stars on GitHub.
- Where can I find Rotated_IoU?
- lilanxiao/Rotated_IoU is on GitHub at https://github.com/lilanxiao/Rotated_IoU.