RUNet: A Robust UNet Architecture for Image Super-Resolution

Hu, Xiaodan; Naiel, Mohamed A.; Wong, Alexander; Lamm, Mark; Fieguth, Paul

doi:10.1109/cvprw.2019.00073

Cited by 78 publications

(58 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system learns the trajectory and reproduces the user's control using the knowledge of a human pilot for training a convolutional neural network (CNN) that receives as input the current camera frame and outputs the next state. The idea is to reinforce the knowledge of the trajectory using a UNET model [41], [42].…”

Section: = [ ]mentioning

confidence: 99%

Indoor Localization and Navigation based on Deep Learning using a Monocular Visual System

Ancona¹,

Corona-Ramírez²,

Frías³

2021

IJACSA

View full text Add to dashboard Cite

Now-a-days, computer systems are important for artificial vision systems to analyze the acquired data to realize crucial tasks, such as localization and navigation. For successful navigation, the robot must interpret the acquired data and determine its position to decide how to move through the environment. This paper proposes an indoor mobile robot visuallocalization and navigation approach for autonomous navigation. A convolutional neural network and background modeling are used to locate the system in the environment. Object detection is based on copy-move detection, an image forensic technique, extracting features from the image to identify similar regions. An adaptive threshold is proposed due to the illumination changes. The detected object is classified to evade it using a control deep neural network. A U-Net model is implemented to track the path trajectory. The experiment results were obtained from real data, proving the efficiency of the proposed algorithm. The adaptive threshold solves illumination variation issues for object detection.

show abstract

Section: = [ ]mentioning

confidence: 99%

Indoor Localization and Navigation based on Deep Learning using a Monocular Visual System

Ancona¹,

Corona-Ramírez²,

Frías³

2021

IJACSA

View full text Add to dashboard Cite

show abstract

“…By concatenating features from the encoding branch with corresponding features on the decoding branch before further processing, details in the data that could get lost during the compression process can be preserved and localized precisely. In recent work, the U-Net architecture has also been employed for super-resolution tasks (e.g., Hu et al, 2019;Lu and Chen, 2019).…”

Section: Deeprumentioning

confidence: 99%

A comparative study of convolutional neural network models for wind field downscaling

Höhlein

Kern

Hewson

et al. 2020

Meteorological Applications

View full text Add to dashboard Cite

We analyze the applicability of convolutional neural network (CNN) architectures for downscaling of short‐range forecasts of near‐surface winds on extended spatial domains. Short‐range wind forecasts (at the 100 m level) from European Centre for Medium Range Weather Forecasts ERA5 reanalysis initial conditions at 31 km horizontal resolution are downscaled to mimic high resolution (HRES) (deterministic) short‐range forecasts at 9 km resolution. We evaluate the downscaling quality of four exemplary CNN architectures and compare these against a multilinear regression model. We conduct a qualitative and quantitative comparison of model predictions and examine whether the predictive skill of CNNs can be enhanced by incorporating additional atmospheric variables, such as geopotential height and forecast surface roughness, or static high‐resolution fields, like land–sea mask and topography. We further propose DeepRU, a novel U‐Net‐based CNN architecture, which is able to infer situation‐dependent wind structures that cannot be reconstructed by other models. Inferring a target 9 km resolution wind field from the low‐resolution input fields over the Alpine area takes less than 10 ms on our graphics processing unit target architecture, which compares favorably to an overhead in simulation time of minutes or hours between low‐ and high‐resolution forecast simulations.

show abstract

“…The UNet network [48] and its variations, which are representative encoder-decoder architectures, have attracted extensive interest in many computer vision tasks, including image segmentation [49]- [51], image SR [52], [53], image generation [54], [55], and object detection [56]. Typically, the UNet network is composed of a contracting path in encoder, an expanding path in decoder, and some skip connections between two paths.…”

Section: Unet and Ynetmentioning

confidence: 99%

Guided Depth Map Super-Resolution Using Recumbent Y Network

Dong

Lin

2020

IEEE Access

View full text Add to dashboard Cite

Low spatial resolution is a well-known problem for depth maps captured by low-cost consumer depth cameras. Depth map super-resolution (SR) can be used to enhance the resolution and improve the quality of depth maps. In this paper, we propose a recumbent Y network (RYNet) to integrate the depth information and intensity information for depth map SR. Specifically, we introduce two weight-shared encoders to respectively learn multi-scale depth and intensity features, and a single decoder to gradually fuse depth information and intensity information for reconstruction. We also design a residual channel attention based atrous spatial pyramid pooling structure to further enrich the feature's scale diversity and exploit the correlations between multi-scale feature channels. Furthermore, the violations of co-occurrence assumption between depth discontinuities and intensity edges will generate texture-transfer and depth-bleeding artifacts. Thus, we propose a spatial attention mechanism to mitigate the artifacts by adaptively learning the spatial relevance between intensity features and depth features and reweighting the intensity features before fusion. Experimental results demonstrate the superiority of the proposed RYNet over several state-of-the-art depth map SR methods. INDEX TERMS Depth map super-resolution, convolutional neural network, UNet network, atrous spatial pyramid pooling, attention mechanism.

show abstract

RUNet: A Robust UNet Architecture for Image Super-Resolution

Cited by 78 publications

References 8 publications

Indoor Localization and Navigation based on Deep Learning using a Monocular Visual System

Indoor Localization and Navigation based on Deep Learning using a Monocular Visual System

A comparative study of convolutional neural network models for wind field downscaling

Guided Depth Map Super-Resolution Using Recumbent Y Network

Contact Info

Product

Resources

About