📖 3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection

🔥The first work to introduce 3D Gaussian Splatting into 3D Object Detection. ⭐Star 3DGS-DET. Thanks🔥

[Paper]  

Yang Cao*, Yuanliang Ju*, Dan Xu
The Hong Kong University of Science and Technology

🚩 Updates

☑ Being Top-5 in Hugging Face Daily Papers!

☐ The code and data will be released within a month of the paper's acceptance. Please stay tuned.

☑ Our paper 3DGS-DET is released, check out it on arXiv.

Table of Contents

• Boundary Guidance
• Pipeline of 3DGS for 3D Object Detection
• Methods
• Detection Samples
• Guidance from Different Priors
• Rendered Images
• BibTeX
• Contact
• Acknowledgement

Boundary Guidance

Pipeline of 3DGS for 3D Object Detection

Methods

Detection Samples

Guidance from Different Priors

Rendered Images

BibTeX

Cite 3DGS-DET by:

@article{cao20243dgs,
  title={3dgs-det: Empower 3d gaussian splatting with boundary guidance and box-focused sampling for 3d object detection},
  author={Cao, Yang and Ju, Yuanliang and Xu, Dan},
  journal={arXiv preprint arXiv:2410.01647},
  year={2024}
}

Contact

If you have any question or collaboration needs, please email yangcao.cs@gmail.com.

Acknowledgement

3DGS-DET is implemented based on 3DGS and MMDetection3D. We appreciate their great codes.