Removing pixel-wise heterogeneous motion blur is challenging due to the ill-posed nature of the problem. The predominant solution is to estimate the blur kernel by adding a prior, but the extensive literature on the subject indicates the difficulty in identifying a prior which is suitably informative, and general. Rather than imposing a prior based on theory, we propose instead to learn one from the data. Learning a prior over the latent image would require modeling all possible image content. The critical observation underpinning our approach is thus that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content. This is a much easier learning task, but it also avoids the iterative process through which latent image priors are typically applied. Our approach directly estimates the motion flow from the blurred image through a fully-convolutional deep neural network (FCN) and recovers the unblurred image from the estimated motion flow. Our FCN is the first universal end-to-end mapping from the blurred image to the dense motion flow. To train the FCN, we simulate motion flows to generate synthetic blurred-image-motion-flow pairs thus avoiding the need for human labeling. Extensive experiments on challenging realistic blurred images demonstrate that the proposed method outperforms the state-of-the-art.

Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes. Previous methods first register the input low dynamic range (LDR) images using optical flow before merging them, which are error-prone and cause ghosts in results. A very recent work tries to bypass optical flows via a deep network with skip-connections, however, which still suffers from ghosting artifacts for severe movement. To avoid the ghosting from the source, we propose a novel attention-guided end-to-end deep neural network (AHDRNet) to produce high-quality ghost-free HDR images. Unlike previous methods directly stacking the LDR images or features for merging, we use attention modules to guide the merging according to the reference image. The attention modules automatically suppress undesired components caused by misalignments and saturation and enhance desirable fine details in the non-reference images. In addition to the attention model, we use dilated residual dense block (DRDB) to make full use of the hierarchical features and increase the receptive field for hallucinating the missing details. The proposed AHDRNet is a non-flowbased method, which can also avoid the artifacts generated by optical-flow estimation error. Experiments on different datasets show that the proposed AHDRNet can achieve state-of-the-art quantitative and qualitative results.

Methylammonium lead iodide perovskite, CH3NH3PbI3, has attracted particular attention because of its fast increase in efficiency as solid-state solar cells. We performed first-principles calculations with the nonlocal van der Waals (vdW) correlation to investigate the crystal structures and electronic and optical properties of CH3NH3PbI3. The calculated results show that the distribution of methylammonium ions, which further changes the vdW interaction and hydrogen bonds of organic and inorganic matrixes, plays a vital role in both the geometry stability and the electronic structure. The vdW correlation is critical to provide appropriate descriptions of the interaction between the organic and the inorganic parts. The phase transformation from orthorhombic to tetragonal phase causes the decrease of the band gap and the red shift of the optical absorption coefficient.

As fuzzy c-means clustering (FCM) algorithm is sensitive to noise, local spatial information is often introduced to an objective function to improve the robustness of the FCM algorithm for image segmentation. However, the introduction of local spatial information often leads to a high computational complexity, arising out of an iterative calculation of the distance between pixels within local spatial neighbors and clustering centers. To address this issue, an improved FCM algorithm based on morphological reconstruction and membership filtering (FRFCM) that is significantly faster and more robust than FCM is proposed in this paper. First, the local spatial information of images is incorporated into FRFCM by introducing morphological reconstruction operation to guarantee noise-immunity and image detail-preservation. Second, the modification of membership partition, based on the distance between pixels within local spatial neighbors and clustering centers, is replaced by local membership filtering that depends only on the spatial neighbors of membership partition. Compared with stateof-the-art algorithms, the proposed FRFCM algorithm is simpler and significantly faster, since it is unnecessary to compute the distance between pixels within local spatial neighbors and clustering centers. In addition, it is efficient for noisy image segmentation because membership filtering are able to improve membership partition matrix efficiently. Experiments performed on synthetic and real-world images demonstrate that the proposed algorithm

No abstract

Stimuli-responsive hydrogels can respond to stimuli by phase transformation or volume change and exhibit specific functions. Near-infrared (NIR)-responsive hydrogel is a type of stimuli-responsive hydrogel, which can be precisely controlled by altering the radiation intensity, exposure time of the light source, and irradiation sites. Here, polydopamine nanoparticles (PDA-NPs) were introduced into a poly(N-isopropylacrylamide) (PNIPAM) network to fabricate a PDA-NPs/PNIPAM hydrogel with NIR responsibility, self-healing ability, and cell/tissue adhesiveness. After incorporation of PDA-NPs into the hydrogel, the PDA-NPs/PNIPAM hydrogel showed phase transitions and volume changes in response to NIR. Thus, the hydrogel can achieve triple response effects, including pulsatile drug release, NIR-driven actuation, and NIR-assisted healing. After coating PDA-NPs onto hydrogel surfaces, the hydrogel showed improved cell affinity, good tissue adhesiveness, and growth factor/protein immobilization ability because of reactive catechol groups on PDA-NPs. The tissue adhesion strength to porcine skin was as high as 90 KPa. In vivo full-skin defect experiments demonstrated that PDA-NPs coating on the hydrogel and an immobilized growth factor had a synergistic effect on accelerating wound healing. In summary, we combined thermosensitive PNIPAM and mussel-inspired PDA-NPs to form a NIR-responsive hydrogel, which may have potential applications for chemical and physical therapies.

A great number of improved fuzzy c-means (FCM) clustering algorithms have been widely used for grayscale and color image segmentation. However, most of them are timeconsuming and unable to provide desired segmentation results for color images due to two reasons. The first one is that the incorporation of local spatial information often causes a high computational complexity due to the repeated distance computation between clustering centers and pixels within a local neighboring window. The other one is that a regular neighboring window usually breaks up the real local spatial structure of images and thus leads to a poor segmentation. In this work, we propose a superpixel-based fast FCM clustering algorithm (SFFCM) that is significantly faster and more robust than stateof-the-art clustering algorithms for color image segmentation. To obtain better local spatial neighborhoods, we firstly define a multiscale morphological gradient reconstruction (MMGR) operation to obtain a superpixel image with accurate contour. In contrast to traditional neighboring window of fixed size and shape, the superpixel image provides better adaptive and irregular local spatial neighborhoods that are helpful for improving color image segmentation. Secondly, based on the obtained superpixel image, the original color image is simplified efficiently and its histogram is computed easily by counting the number of pixels in each region of the superpixel image. Finally, we implement FCM with histogram parameter on the superpixel image to obtain the final segmentation result. Experiments performed on synthetic images and real images demonstrate that the proposed algorithm provides better segmentation results and takes less time than state-of-the-art clustering algorithms for color image segmentation.

The Haber−Bosch process for industrial NH 3 production suffers from harsh reaction conditions and serious CO 2 emission. Electrochemical N 2 reduction offers a carbon-neutral alternative for more energy-saving NH 3 synthesis but requires active electrocatalysts for the N 2 reduction reaction (NRR). In this Letter, boron nanosheet (BNS) is proposed as an elemental two-dimensional (2D) material to effectively catalyze the NRR toward NH 3 synthesis with excellent selectivity. When tested in 0.1 M Na 2 SO 4 , such BNS catalyst attains a high Faradaic efficiency of 4.04% and a large NH 3 yield of 13.22 μg h −1 mg cat −1 at −0.80 V vs reversible hydrogen electrode, with strong electrochemical durability. Density functional theory calculations suggest that the B atoms of both oxidized and H-deactivated BNS can catalyze the NRR more effectively than clean BNS, and the rate-determining step is the desorption process of the second NH 3 gas.