A5054397516- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Image and Signal Denoising Methods
- Hydraulic Fracturing and Reservoir Analysis
- Enhanced Oil Recovery Techniques
- Image Processing Techniques and Applications
- CO2 Sequestration and Geologic Interactions
- Drilling and Well Engineering
- Groundwater flow and contamination studies
- Methane Hydrates and Related Phenomena
- Geothermal Energy Systems and Applications
- Hydrocarbon exploration and reservoir analysis
- Oil and Gas Production Techniques
- Calcium Carbonate Crystallization and Inhibition
- Concrete Corrosion and Durability
- Corrosion Behavior and Inhibition
- Offshore Engineering and Technologies
- Diverse Research and Applications
University of Würzburg
2023
East China Normal University
2023
Shanghai Key Laboratory of Trustworthy Computing
2023
China University of Petroleum, East China
2020-2022
This paper introduces a novel benchmark for efficient up-scaling as part of the NTIRE 2023 Real-Time Image Super-Resolution (RTSR) Challenge, which aimed to upscale images from 720p and 1080p resolution native 4K (×2 ×3 factors) in real-time on commercial GPUs. For this, we use new test set containing diverse ranging digital art gaming photography. We assessed methods devised SR by measuring their runtime, parameters, FLOPs, while ensuring minimum PSNR fidelity over Bicubic interpolation....
In recent years, there has been an increasing demand for real-time super-resolution networks on mobile devices. To address this issue, many lightweight models have proposed. However, these still contain time-consuming components that increase inference latency, limiting their real-world applications paper, we propose a novel model single-image based Equivalent Transformation and Dual Stream network construction (ETDS). ET method is proposed to transform operators into time-friendly...
When both of the scaling and hydrate risks occur in deep-water wells or subsea pipelines at same time, compatibility between scale inhibitors should be paid more attention to for risk prevention. In this paper, a new gas field found South China Sea is taken as reference project background investigate experimentally. Firstly preliminary qualification evaluation was carried out, which static inhibition efficiency, induction minimum effective concentrations selected were tested. Then effect...
Deep convolutional neural networks (CNNs) have achieved unprecedented success in single image super-resolution over the past few years. Meanwhile, there is an increasing demand for with arbitrary scale factors real-world scenarios. Many approaches adopt scale-specific multi-path learning to cope multi-scale a network. However, these methods require large number of parameters. To achieve better balance between reconstruction quality and parameter amounts, we proposes learnable interpolation...
With the increasing availability of devices that support ultra-high-definition (UHD) images, Single Image Super Resolution (SISR) has emerged as a crucial problem in field computer vision. In recent years, CNN-based super resolution approaches have made significant advances, producing high-quality upscaled images. However, these methods can be computationally and memory intensive, making them impractical for real-time applications such upscaling to UHD The performance reconstruction quality...
Self-circulation wellbore is a new technique for geothermal development in hot dry rocks (HDR), which uses U-shape channel composed of tubing and casing as the heat exchanger. In this study, self-circulation HDR on laboratory scale was built, serial experiments were conducted to investigate exchange law influencing factors mining rate wellbore. A similarity analysis also made estimate heat-mining capacity field scale. The experimental results show that large thermal conductivity granite with...
Blind super-resolution, different from conventional non-blind super-resolution based on the assumption of fixed degradation, handles various unknown Gaussian blur kernels, and thus is closer to real-world application. The accuracy kernel estimation deconvolution directly influences performance overall results, but recent works usually introduce artifacts during process. In this paper, we propose our methods a more accurate module (KEM) (DM). Additionally, KEM DM are embedded in structure...
The Xining Basin in Qinghai Province, China, is rich mid–low temperature geothermal resources, but the reinjection of water has not yet started. In this paper, physical properties rocks sampled from newly drilled well DR2018 were analyzed, and a series core flooding experiments was conducted to assess formation blockage risk during reinjection. experimental results show that reservoir low porosity 1.64–18.68% permeability 0.04–7.23 md. are weakly consolidated, movable clay sand particles...
Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale enhance low-resolution images video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power NPUs having many computational memory constraints. In Mobile AI challenge, we address propose participants design an efficient quantized image solution that can demonstrate real-time performance NPUs. The were provided DIV2K...