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.
Cite
Text
Brebion et al. "DELTA: Dense Depth from Events and LiDAR Using Transformer's Attention." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.Markdown
[Brebion et al. "DELTA: Dense Depth from Events and LiDAR Using Transformer's Attention." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/brebion2025cvprw-delta/)BibTeX
@inproceedings{brebion2025cvprw-delta,
title = {{DELTA: Dense Depth from Events and LiDAR Using Transformer's Attention}},
author = {Brebion, Vincent and Moreau, Julien and Davoine, Franck},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2025},
pages = {4898-4907},
url = {https://mlanthology.org/cvprw/2025/brebion2025cvprw-delta/}
}