ShoufaChen/DiffusionDet
PyTorch implementation of DiffusionDet, a diffusion model for object detection that treats bounding box prediction as a denoising diffusion process.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official PyTorch implementation of DiffusionDet, applying diffusion models to object detection tasks. The approach frames object detection as a denoising diffusion process where bounding boxes are refined from random noise over multiple steps. It supports multiple backbone architectures including ResNet and Swin Transformer, and evaluates on COCO and LVIS benchmarks. The work was published at ICCV 2023.
Frequently asked
- What is ShoufaChen/DiffusionDet?
- PyTorch implementation of DiffusionDet, a diffusion model for object detection that treats bounding box prediction as a denoising diffusion process.
- Is DiffusionDet open source?
- Yes — ShoufaChen/DiffusionDet is an open-source project tracked on heatdrop.
- What language is DiffusionDet written in?
- ShoufaChen/DiffusionDet is primarily written in Python.
- How popular is DiffusionDet?
- ShoufaChen/DiffusionDet has 2.3k stars on GitHub.
- Where can I find DiffusionDet?
- ShoufaChen/DiffusionDet is on GitHub at https://github.com/ShoufaChen/DiffusionDet.