Journal article · 2025 · Open access

DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection

Peng Zhi, Xiaowei Xu, Hongtao Nie, Binbin Yong, Jun Shen, Qingguo Zhou

Tsinghua Science & Technology, 31(2), 760–776 · Published 21 October 2025 · DOI 10.26599/tst.2024.9010173

Open PDFView at the publisherCite this paper

In brief

“DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection” is a 2025 journal article by Peng Zhi and 5 co-authors, published in Tsinghua Science & Technology. OpenAlex counts 5 citations as of 22 November 2026, which puts it in the top 3% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Tsinghua Science & Technology.

Citations
5
Most cited in
2026 (5)
Field-weighted impact
0.87
References
45
Authors
6

Abstract

As a typical application of edge intelligence, 3D object detection in autonomous driving often requires multimodal information fusion to accurately perceive the environment. With images and point clouds serving as critical sensory data sources, 3D object detection integrates multimodal fusion to enhance detection accuracy. Generally, fusion algorithms leveraging attention mechanism can intelligently extract and integrate multimodal sensing information to overcome limitations posed by sensor calibration. However, attention mechanism may cause challenges such as slow model convergence and high false positives. Therefore, in this paper, we propose the deformable denoising (DefDeN) model to effectively integrate modules including gated information fusion networks, multi-scale deformable attention mechanisms, noise addition and denoising method, and contrastive learning for multi-sensor feature fusion. Experimental results on the nuScenes dataset demonstrate the superiority of DefDeN in detection accuracy, and the effectiveness of precise and stable perception for complex scenarios in autonomous driving systems.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zhi, P., Xu, X., Nie, H., Yong, B., Shen, J., & Zhou, Q. (2025). DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection. Tsinghua Science & Technology, 31(2), 760–776. https://doi.org/10.26599/tst.2024.9010173

MLA 9

Zhi, Peng, et al. “DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection.” Tsinghua Science & Technology, vol. 31, no. 2, 2025, pp. 760–776. https://doi.org/10.26599/tst.2024.9010173.

Chicago

Zhi, Peng, Xiaowei Xu, Hongtao Nie, Binbin Yong, Jun Shen, and Qingguo Zhou. 2025. “DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection.” Tsinghua Science & Technology 31 (2): 760–776. https://doi.org/10.26599/tst.2024.9010173.

Harvard

Zhi, P. et al. (2025) ‘DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection’, Tsinghua Science & Technology, 31(2), pp. 760–776. doi:10.26599/tst.2024.9010173.

IEEE

P. Zhi, X. Xu, H. Nie, B. Yong, J. Shen, and Q. Zhou, “DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection,” Tsinghua Science & Technology, vol. 31, no. 2, pp. 760–776, 2025, doi: 10.26599/tst.2024.9010173.

BibTeX

@article{zhi2025defden,
  title     = {{DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection}},
  author    = {Zhi, Peng and Xu, Xiaowei and Nie, Hongtao and Yong, Binbin and Shen, Jun and Zhou, Qingguo},
  journal   = {Tsinghua Science \& Technology},
  year      = {2025},
  volume    = {31},
  number    = {2},
  pages     = {760--776},
  doi       = {10.26599/tst.2024.9010173},
  url       = {https://doi.org/10.26599/tst.2024.9010173}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety

  • 3D object detection
  • LiDAR-camera fusion
  • multimodal fusion
  • deformable attention
  • contrastive learning
  • autonomous driving perception
  • edge AI
  • nuScenes

Work with this paper

Most-cited papers in Engineering

All highly cited Engineering papers

Questions about this paper

How do I cite this paper in APA style?

Zhi, P., Xu, X., Nie, H., Yong, B., Shen, J., & Zhou, Q. (2025). DefDeN: A Deformable Denoising-Based LiDAR and Camera Feature Fusion Model for 3D Object Detection. Tsinghua Science & Technology, 31(2), 760–776. https://doi.org/10.26599/tst.2024.9010173

How many times has this paper been cited?

5 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Tsinghua Science & Technology: sign in and open the PDF from this page.

Who wrote this paper?

Peng Zhi, Xiaowei Xu, Hongtao Nie, Binbin Yong, Jun Shen, Qingguo Zhou.

What is the DOI of this paper?

10.26599/tst.2024.9010173, permanently at https://doi.org/10.26599/tst.2024.9010173. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.