| Issue |
EPJ Web Conf.
Volume 341, 2025
2nd International Conference on Advent Trends in Computational Intelligence and Communication Technologies (ICATCICT 2025)
|
|
|---|---|---|
| Article Number | 01006 | |
| Number of page(s) | 12 | |
| DOI | https://doi.org/10.1051/epjconf/202534101006 | |
| Published online | 20 November 2025 | |
https://doi.org/10.1051/epjconf/202534101006
Depth Perception Using Various Vision Transformer
Department of Computer Science & Engineering, Amity University, Mumbai, India
* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.
Published online: 20 November 2025
Abstract
Proper depth perception is one of the key requirements of three-dimensional understanding of scenes in the context of self-driving. The discussed manuscript defines a re-architecturing of VoxelNet with a dual attention paradigm (inspired by Vision Transformers (ViT)) added to capture long-range relationships and context-sensitive features. The combined use of channel-wise and location attention modules in encoding voxel features produces improvements in the effectiveness of object characterization and location of objects. Empirical analyses performed on the KITTI 3D dataset demonstrates that there can be observed better results in depth-perception accuracy and mean average-precision in the pedestrian, cyclist and vehicular categories.
Key words: Depth / Perception3D / Object Detection / Encoding / LiDAR Global / Context / Modeling / Vision Transformer (ViT)
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.