Cargando…
DTS-Net: Depth-to-Space Networks for Fast and Accurate Semantic Object Segmentation
We propose Depth-to-Space Net (DTS-Net), an effective technique for semantic segmentation using the efficient sub-pixel convolutional neural network. This technique is inspired by depth-to-space (DTS) image reconstruction, which was originally used for image and video super-resolution tasks, combine...
Autores principales: | Ibrahem, Hatem, Salem, Ahmed, Kang, Hyun-Soo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8749585/ https://www.ncbi.nlm.nih.gov/pubmed/35009879 http://dx.doi.org/10.3390/s22010337 |
Ejemplares similares
-
DTS-Depth: Real-Time Single-Image Depth Estimation Using Depth-to-Space Image Construction
por: Ibrahem, Hatem, et al.
Publicado: (2022) -
LEOD-Net: Learning Line-Encoded Bounding Boxes for Real-Time Object Detection
por: Ibrahem, Hatem, et al.
Publicado: (2022) -
Exploration of Semantic Label Decomposition and Dataset Size in Semantic Indoor Scenes Synthesis via Optimized Residual Generative Adversarial Networks
por: Ibrahem, Hatem, et al.
Publicado: (2022) -
RT-ViT: Real-Time Monocular Depth Estimation Using Lightweight Vision Transformers
por: Ibrahem, Hatem, et al.
Publicado: (2022) -
FASSVid: Fast and Accurate Semantic Segmentation for Video Sequences
por: Portillo-Portillo, Jose, et al.
Publicado: (2022)