DELTA: Dense Depth from Events and LiDAR Using Transformer's Attention
Uložené v:
| Názov: | DELTA: Dense Depth from Events and LiDAR Using Transformer's Attention |
|---|---|
| Autori: | Brebion, Vincent, Moreau, Julien, Davoine, Franck |
| Prispievatelia: | Brebion, Vincent |
| Zdroj: | 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). :4898-4907 |
| Publication Status: | Preprint |
| Informácie o vydavateľovi: | IEEE, 2025. |
| Rok vydania: | 2025 |
| Predmety: | FOS: Computer and information sciences, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, I.4.8, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] |
| Popis: | 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. Accepted for the CVPR 2025 Workshop on Event-based Vision. For the project page, see https://vbrebion.github.io/DELTA/ |
| Druh dokumentu: | Article Conference object |
| Popis súboru: | application/pdf |
| DOI: | 10.1109/cvprw67362.2025.00482 |
| DOI: | 10.48550/arxiv.2505.02593 |
| Prístupová URL adresa: | http://arxiv.org/abs/2505.02593 https://hal.science/hal-05057148v1/document https://hal.science/hal-05057148v1 |
| Rights: | STM Policy #29 CC BY |
| Prístupové číslo: | edsair.doi.dedup.....fe92df14d688ca0dd17bc8007de5e8c9 |
| Databáza: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | 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.<br />Accepted for the CVPR 2025 Workshop on Event-based Vision. For the project page, see https://vbrebion.github.io/DELTA/ |
|---|---|
| DOI: | 10.1109/cvprw67362.2025.00482 |