Cargando…
Color-Guided Depth Map Super-Resolution Using a Dual-Branch Multi-Scale Residual Network with Channel Interaction
We designed an end-to-end dual-branch residual network architecture that inputs a low-resolution (LR) depth map and a corresponding high-resolution (HR) color image separately into the two branches, and outputs an HR depth map through a multi-scale, channel-wise feature extraction, interaction, and...
Autores principales: | Chen, Ruijin, Gao, Wei |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7146598/ https://www.ncbi.nlm.nih.gov/pubmed/32168872 http://dx.doi.org/10.3390/s20061560 |
Ejemplares similares
-
Fully Cross-Attention Transformer for Guided Depth Super-Resolution
por: Ariav, Ido, et al.
Publicado: (2023) -
Adaptive Aggregate Stereo Matching Network with Depth Map Super-Resolution
por: Liu, Botao, et al.
Publicado: (2022) -
Depth Completion and Super-Resolution with Arbitrary Scale Factors for Indoor Scenes †
por: Truong, Anh Minh, et al.
Publicado: (2021) -
Multiscale Attention Fusion for Depth Map Super-Resolution Generative Adversarial Networks
por: Xu, Dan, et al.
Publicado: (2023) -
Image Super-Resolution via Dual-Level Recurrent Residual Networks
por: Tan, Congming, et al.
Publicado: (2022)