Preprint · 2024 · Open access

Progressive Multi-Modal Fusion for Robust 3D Object Detection

Rohit Mohan, Daniele Cattaneo, Florian Drews, Abhinav Valada

arXiv (Cornell University) · Published 9 October 2024 · DOI 10.48550/arxiv.2410.07475

Open PDFView at the publisherCite this paper

In brief

“Progressive Multi-Modal Fusion for Robust 3D Object Detection” is a 2024 preprint by Rohit Mohan and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 17 citations as of 22 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
17
Most cited in
2026 (9)
References
52
Authors
4

Abstract

Multi-sensor fusion is crucial for accurate 3D object detection in autonomous driving, with cameras and LiDAR being the most commonly used sensors. However, existing methods perform sensor fusion in a single view by projecting features from both modalities either in Bird's Eye View (BEV) or Perspective View (PV), thus sacrificing complementary information such as height or geometric proportions. To address this limitation, we propose ProFusion3D, a progressive fusion framework that combines features in both BEV and PV at both intermediate and object query levels. Our architecture hierarchically fuses local and global features, enhancing the robustness of 3D object detection. Additionally, we introduce a self-supervised mask modeling pre-training strategy to improve multi-modal representation learning and data efficiency through three novel objectives. Extensive experiments on nuScenes and Argoverse2 datasets conclusively demonstrate the efficacy of ProFusion3D. Moreover, ProFusion3D is robust to sensor failure, demonstrating strong performance when only one modality is available.

Cite this paper

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

APA 7

Mohan, R., Cattaneo, D., Drews, F., & Valada, A. (2024). Progressive Multi-Modal Fusion for Robust 3D Object Detection. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.07475

MLA 9

Mohan, Rohit, et al. “Progressive Multi-Modal Fusion for Robust 3D Object Detection.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2410.07475.

Chicago

Mohan, Rohit, Daniele Cattaneo, Florian Drews, and Abhinav Valada. 2024. “Progressive Multi-Modal Fusion for Robust 3D Object Detection.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.07475.

Harvard

Mohan, R. et al. (2024) ‘Progressive Multi-Modal Fusion for Robust 3D Object Detection’, arXiv (Cornell University). doi:10.48550/arxiv.2410.07475.

IEEE

R. Mohan, D. Cattaneo, F. Drews, and A. Valada, “Progressive Multi-Modal Fusion for Robust 3D Object Detection,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2410.07475.

BibTeX

@misc{mohan2024progressive,
  title     = {{Progressive Multi-Modal Fusion for Robust 3D Object Detection}},
  author    = {Mohan, Rohit and Cattaneo, Daniele and Drews, Florian and Valada, Abhinav},
  howpublished = {arXiv (Cornell University)},
  year      = {2024},
  doi       = {10.48550/arxiv.2410.07475},
  url       = {https://doi.org/10.48550/arxiv.2410.07475}
}

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

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • 3D object detection
  • multi-sensor fusion
  • LiDAR-camera fusion
  • progressive feature fusion
  • bird's-eye view
  • perspective view
  • self-supervised pre-training
  • autonomous driving

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Mohan, R., Cattaneo, D., Drews, F., & Valada, A. (2024). Progressive Multi-Modal Fusion for Robust 3D Object Detection. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.07475

How many times has this paper been cited?

17 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Rohit Mohan, Daniele Cattaneo, Florian Drews, Abhinav Valada.

What is the DOI of this paper?

10.48550/arxiv.2410.07475, permanently at https://doi.org/10.48550/arxiv.2410.07475. 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.