DELTA: Dense Depth from Events and LiDAR using Transformer's Attention

---

Abstract

Event cameras and LiDARs provide complementary yet distinct data: respectively, asynchronous detections of changes in lighting versus sparse but accurate depth information at a fixed rate. To this day, few works have explored the combination of these two modalities. In this article, we propose a novel neural-network-based method for fusing event and LiDAR data in order to estimate dense depth maps. Our architecture, DELTA, exploits the concepts of self- and cross-attention to model the spatial and temporal relations within and between the event and LiDAR data. Following a thorough evaluation, we demonstrate that DELTA sets a new state of the art in the event-based depth estimation problem, and that it is able to reduce the errors up to four times for close ranges compared to the previous SOTA.

---

Citation

@article{Brebion2025DELTADD,
  title={{DELTA}: Dense Depth from Events and {LiDAR} using Transformer's Attention},
  author={Vincent Brebion and Julien Moreau and Franck Davoine},
  journal={2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  pages={x-x},
  year={2025}
}

---

Acknowledgment

This work was supported in part by the Hauts-de-France Region and in part by the SIVALab Joint Laboratory (Renault Group - Université de technologie de Compiègne (UTC) - Centre National de la Recherche Scientifique (CNRS)).
This work was also supported by The Royal Physiographic Society in Lund.