Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution.

Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on face SR, but is prone to produce artifacts upon challenging cases in real-world scenarios, since joint participation in the same degradation branch will impact final performance due to huge domain gap between real-world and synthetic LR ones obtained by generators. To better exploit the powerful generative capability of GAN for real-world face SR, in this paper, we establish two independent degradation branches in the forward and backward cycle-consistent reconstruction processes, respectively, while the two processes share the same restoration branch. Our Semi-Cycled Generative Adversarial Networks (SCGAN) is able to alleviate the adverse effects of the domain gap between the real-world LR face images and the synthetic LR ones, and to achieve accurate and robust face SR performance by the shared restoration branch regularized by both the forward and backward cycle-consistent learning processes. Experiments on two synthetic and two real-world datasets demonstrate that, our SCGAN outperforms the state-of-the-art methods on recovering the face structures/details and quantitative metrics for real-world face SR. The code will be publicly released at https://github.com/HaoHou-98/SCGAN.

STAR: A Structure and Texture Aware Retinex Model.

Retinex theory is developed mainly to decompose an image into the illumination and reflectance components by analyzing local image derivatives. In this theory, larger derivatives are attributed to the changes in reflectance, while smaller derivatives are emerged in the smooth illumination. In this paper, we utilize exponentiated local derivatives (with an exponent γ) of an observed image to generate its structure map and texture map. The structure map is produced by been amplified with γ > 1, while the texture map is generated by been shrank with γ < 1. To this end, we design exponential filters for the local derivatives, and present their capability on extracting accurate structure and texture maps, influenced by the choices of exponents γ. The extracted structure and texture maps are employed to regularize the illumination and reflectance components in Retinex decomposition. A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image. We solve the STAR model by an alternating optimization algorithm. Each sub-problem is transformed into a vectorized least squares regression, with closed-form solutions. Comprehensive experiments on commonly tested datasets demonstrate that, the proposed STAR model produce better quantitative and qualitative performance than previous competing methods, on illumination and reflectance decomposition, low-light image enhancement, and color correction. The code is publicly available at https://github.com/csjunxu/STAR.

Image denoising with morphology- and size-adaptive block-matching transform domain filtering.

BM3D is a state-of-the-art image denoising method. Its denoised results in the regions with strong edges can often be better than in the regions with smooth or weak edges, due to more accurate block-matching for the strong-edge regions. So using adaptive block sizes on different image regions may result in better image denoising. Based on these observations, in this paper, we first partition each image into regions belonging to one of the three morphological components, i.e., contour, texture, and smooth components, according to the regional energy of alternating current (AC) coefficients of discrete cosine transform (DCT). Then, we can adaptively determine the block size for each morphological component. Specifically, we use the smallest block size for the contour components, the medium block size for the texture components, and the largest block size for the smooth components. To better preserve image details, we also use a multi-stage strategy to implement image denoising, where every stage is similar to the BM3D method, except using adaptive sizes and different transform dimensions. Experimental results show that our proposed algorithm can achieve higher PSNR and MSSIM values than the BM3D method, and also better visual quality of denoised images than by the BM3D method and some other existing state-of-the-art methods.

Enhancement of Perivascular Spaces in 7 T MR Image using Haar Transform of Non-local Cubes and Block-matching Filtering.

Perivascular spaces (PVSs) in brain have a close relationship with typical neurological diseases. The quantitative studies of PVSs are meaningful but usually difficult, due to their thin and weak signals and also background noise in the 7 T brain magnetic resonance images (MRI). To clearly distinguish the PVSs in the 7 T MRI, we propose a novel PVS enhancement method based on the Haar transform of non-local cubes. Specifically, we extract a certain number of cubes from a small neighbor to form a cube group, and then perform Haar transform on each cube group. The Haar transform coefficients are processed using a nonlinear function to amplify the weak signals relevant to the PVSs and to suppress the noise. The enhanced image is reconstructed using the inverse Haar transform of the processed coefficients. Finally, we perform a block-matching 4D filtering on the enhanced image to further remove any remaining noise, and thus obtain an enhanced and denoised 7 T MRI for PVS segmentation. We apply two existing methods to complete PVS segmentation, i.e., (1) vesselness-thresholding and (2) random forest classification. The experimental results show that the PVS segmentation performances can be significantly improved by using the enhanced and denoised 7 T MRI.

Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator.

Compressed sensing MRI (CS-MRI) has shown great potential in reducing data acquisition time in MRI. Sparsity or compressibility plays an important role to reduce the image reconstruction error. Conventional CS-MRI typically uses a pre-defined sparsifying transform such as wavelet or finite difference, which sometimes does not lead to a sufficient sparse representation for the image to be reconstructed. In this paper, we design a patch-based nonlocal operator (PANO) to sparsify magnetic resonance images by making use of the similarity of image patches. The definition of PANO results in sparse representation for similar patches and allows us to establish a general formulation to trade the sparsity of these patches with the data consistency. It also provides feasibility to incorporate prior information learnt from undersampled data or another contrast image, which leads to optimized sparse representation of images to be reconstructed. Simulation results on in vivo data demonstrate that the proposed method achieves lower reconstruction error and higher visual quality than conventional CS-MRI methods.

Iodine-129 in seawater offshore Fukushima: distribution, inorganic speciation, sources, and budget.

The Fukushima nuclear accident in March 2011 has released a large amount of radioactive pollutants to the environment. Of the pollutants, iodine-129 is a long-lived radionuclide and will remain in the environment for millions of years. This work first report levels and inorganic speciation of (129)I in seawater depth profiles collected offshore Fukushima in June 2011. Significantly elevated (129)I concentrations in surface water were observed with the highest (129)I/(127)I atomic ratio of 2.2 × 10(-9) in the surface seawater 40 km offshore Fukushima. Iodide was found as the dominant species of (129)I, while stable (127)I was mainly in iodate form, reflecting the fact that the major source of (129)I is the direct liquid discharges from the Fukushima NPP. The amount of (129)I directly discharged from the Fukushima Dai-ichi nuclear power plant to the sea was estimated to be 2.35 GBq, and about 1.09 GBq of (129)I released to the atmosphere from the accident was deposited in the sea offshore Fukushima. A total release of 8.06 GBq (or 1.2 kg) of (129)I from the Fukushima accident was estimated. These Fukushima-derived (129)I data provide necessary information for the investigation of water circulation and geochemical cycle of iodine in the northwestern Pacific Ocean in the future.

Research on similarity measurement for texture image retrieval.

A complete texture image retrieval system includes two techniques: texture feature extraction and similarity measurement. Specifically, similarity measurement is a key problem for texture image retrieval study. In this paper, we present an effective similarity measurement formula. The MIT vision texture database, the Brodatz texture database, and the Outex texture database were used to verify the retrieval performance of the proposed similarity measurement method. Dual-tree complex wavelet transform and nonsubsampled contourlet transform were used to extract texture features. Experimental results show that the proposed similarity measurement method achieves better retrieval performance than some existing similarity measurement methods.

Undersampled MRI reconstruction with patch-based directional wavelets.

Compressed sensing has shown great potential in reducing data acquisition time in magnetic resonance imaging (MRI). In traditional compressed sensing MRI methods, an image is reconstructed by enforcing its sparse representation with respect to a preconstructed basis or dictionary. In this paper, patch-based directional wavelets are proposed to reconstruct images from undersampled k-space data. A parameter of patch-based directional wavelets, indicating the geometric direction of each patch, is trained from the reconstructed image using conventional compressed sensing MRI methods and incorporated into the sparsifying transform to provide the sparse representation for the image to be reconstructed. A reconstruction formulation is proposed and solved via an efficient alternating direction algorithm. Simulation results on phantom and in vivo data indicate that the proposed method outperforms conventional compressed sensing MRI methods in preserving the edges and suppressing the noise. Besides, the proposed method is not sensitive to the initial image when training directions.

Comments on "Image denoising by sparse 3-D transform-domain collaborative filtering".

In order to resolve the problem that the denoising performance has a sharp drop when noise standard deviation reaches 40, proposed to replace the wavelet transform by the DCT. In this comment, we argue that this replacement is unnecessary, and that the problem can be solved by adjusting some numerical parameters. We also present this parameter modification approach here. Experimental results demonstrate that the proposed modification achieves better results in terms of both peak signal-to-noise ratio and subjective visual quality than the original method for strong noise.