This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image ...with a magnification factor of ×4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution.
We compute the effective good divisibility of a rational homogeneous variety, extending an earlier result for complex Grassmannians by Naldi and Occhetta. Non-existence of nonconstant morphisms to ...rational homogeneous varieties of classical Lie type are obtained as applications.
We propose a novel architecture to handle the problem of multi-frame super-resolution (MFSR). The proposed framework is known as Enhanced Burst Super-Resolution (EBSR), which divides the MFSR problem ...into three parts: alignment, fusion, and reconstruction. We propose a Feature Enhanced Pyramid Cascading and Deformable convolution (FEPCD) module to align multiple low-resolution burst images in the feature level. And then the aligned features are fused by a Cross Non-Local Fusion (CNLF) module. Finally, the SR image is reconstructed by the Long Range Concatenation Network (LRCN). In addition, we build a cascading residual pathway structure (CR) to improve the performance. We conduct several experiments to analyze and demonstrate these modules. Our EBSR model won the champion in the real track and second place in the synthetic track in the NTIRE21 Burst Super-Resolution Challenge.
Mixed epithelial and stromal tumor of the kidney (MESTK) is a rare complex renal neoplasm composed of a mixture of cystic and solid components. Until date only few cases of MESTK have been reported. ...We present here a rare case of MESTK that was diagnosed in a 56-year-old female. The patients were referred to our hospital due to a mass on the right kidney identified incidentally in a routine physical examination. A pre-operative diagnosis of cystic renal cell carcinoma was made and a right radical nephrectomy was carried out. Macroscopically, a cystic tumor was noticed in the upper portion of the right kidney. Various-sized cysts accompanied by multiple cysts and few solid areas were observed. Immunohistochemically, various epithelial markers as well as stromal markers were identified. Taken together with all the immunohistochemical results and morphological pattern of the tumor, a diagnosis of MESTK was made. MESTK is relatively rare and generally benign. However, it is difficult to distinguish between benign or malignant tumors according to the current radiological method. Therefore a complete resection of the tumor by partial or radical nephrectomy is suggested.
Dense 3D face reconstruction plays a fundamental role in visual media production involving digital actors. We improve upon high fidelity reconstruction from a single 2D photo with a reconstruction ...framework that is robust to large variations in expressions, poses and illumination. We provide a global optimization step improving the alignment of 3D facial geometry to tracked 2D landmarks with 3D Laplacian deformation. Face detail is improved through, extending Shape from Shading reconstruction with fitted albedo prior masks, together with a fast proportionality constraint between depth and image gradients consistent with local self-occlusion behavior. Together these measures better preserve the crucial facial features that define an actor's identity, and we illustrate this through a variety of comparisons with related works.
Wastewater treatment processes (WWTPs) is considered as a complex control problem due to the strong nonlinearities, uncertainties, and disturbances. In this paper, a hierarchical control strategy ...based on Linear Extension Observer (LESO) and Fast Terminal Sliding Mode Control (FTSMC) is studied to achieve the objectives of reducing the energy consumption (EC) and enhancing the effluent quality (EQ) in WWTPs. Firstly, a Fast Terminal Sliding Mode Control based on LESO (FTSMC-LESO) is designed as the lower layer of the control strategy, and the stability is proved by Lyapunov theory. Then, an optimization function for dissolved oxygen (DO) setpoint is investigated as the upper layer to optimize the setpoint in real time. Finally, simulations are conducted to verify the effectiveness of the hierarchical control strategy on the Benchmark Simulation Model No.1 (BSM1). The experimental results show that compared with the default PI control, the designed control strategy can realize stable control of wastewater treatment process and simultaneously improve EC and EQ.
This paper reviews the first challenge on high-dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2021. ...This manuscript focuses on the newly introduced dataset, the proposed methods and their results. The challenge aims at estimating a HDR image from one or multiple respective low-dynamic range (LDR) observations, which might suffer from under-or over-exposed regions and different sources of noise. The challenge is composed by two tracks: In Track 1 only a single LDR image is provided as input, whereas in Track 2 three differently-exposed LDR images with inter-frame motion are available. In both tracks, the ultimate goal is to achieve the best objective HDR reconstruction in terms of PSNR with respect to a ground-truth image, evaluated both directly and with a canonical tonemapping operation.
Digital Twin brings a new realization approach to the modeling of mobile networks. Mobile networks, as complex systems comprising multiple components, such as mobile users, base stations, and ...wireless environments, have intricate interactions and relationships with each other. By creating a virtual replica of each physical mobile network entity in a virtual space, we build a scalable digital twin system for mobile networks with generative AI. The system can interact with multiple optimizers to evaluate and display real-time simulation results. A companion video can be accessed using the link below. https://youtu.be/xtcBIXPzvkc
PDF
