Cargando…
Voxel Transformer with Density-Aware Deformable Attention for 3D Object Detection
The Voxel Transformer (VoTr) is a prominent model in the field of 3D object detection, employing a transformer-based architecture to comprehend long-range voxel relationships through self-attention. However, despite its expanded receptive field, VoTr’s flexibility is constrained by its predefined re...
Autores principales: | Kim, Taeho, Kim, Joohee |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10458770/ https://www.ncbi.nlm.nih.gov/pubmed/37631754 http://dx.doi.org/10.3390/s23167217 |
Ejemplares similares
-
Voxel-FPN: Multi-Scale Voxel Feature Aggregation for 3D Object Detection from LIDAR Point Clouds
por: Kuang, Hongwu, et al.
Publicado: (2020) -
Boosting 3D Object Detection with Density-Aware Semantics-Augmented Set Abstraction
por: Zhang, Tingyu, et al.
Publicado: (2023) -
Object Detection Based on Swin Deformable Transformer-BiPAFPN-YOLOX
por: Shi, Peicheng, et al.
Publicado: (2023) -
Spatial Attention Frustum: A 3D Object Detection Method Focusing on Occluded Objects
por: He, Xinglei, et al.
Publicado: (2022) -
Focal DETR: Target-Aware Token Design for Transformer-Based Object Detection
por: Xie, Tianming, et al.
Publicado: (2022)