arXiv subjects

Xuan Xu

Publications and source records attributed to Xuan Xu.

22 records · Page 2Linked to original sources

arXiv2020

Deformable Kernel Convolutional Network for Video Extreme Super-Resolution

Video super-resolution, which attempts to reconstruct high-resolution video frames from their corresponding low-resolution versions, has received increasingly more attention in recent years. Most existing approaches opt to use deformable convolution to temporally align neighboring frames and apply traditional spatial attention mechanism (convolution based) to enhance reconstructed features. However, such spatial-only strategies cannot fully utilize temporal dependency among video frames. In this paper, we propose a novel deep learning based VSR algorithm, named Deformable Kernel Spatial Attention Network (DKSAN). Thanks to newly designed Deformable Kernel Convolution Alignment (DKC_Align) and Deformable Kernel Spatial Attention (DKSA) modules, DKSAN can better exploit both spatial and temporal redundancies to facilitate the information propagation across different layers. We have tested DKSAN on AIM2020 Video Extreme Super-Resolution Challenge to super-resolve videos with a scale factor as large as 16. Experimental results demonstrate that our proposed DKSAN can achieve both better subjective and objective performance compared with the existing state-of-the-art EDVR on Vid3oC and IntVID datasets.

cs.CV↗

arXiv2020

AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results

This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020. Common scaling factors for learned video super-resolution (VSR) do not go beyond factor 4. Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details. The task in this challenge is to upscale videos with an extreme factor of 16, which results in more serious degradations that also affect the structural integrity of the videos. A single pixel in the low-resolution (LR) domain corresponds to 256 pixels in the high-resolution (HR) domain. Due to this massive information loss, it is hard to accurately restore the missing information. Track 1 is set up to gauge the state-of-the-art for such a demanding task, where fidelity to the ground truth is measured by PSNR and SSIM. Perceptually higher quality can be achieved in trade-off for fidelity by generating plausible high-frequency content. Track 2 therefore aims at generating visually pleasing results, which are ranked according to human perception, evaluated by a user study. In contrast to single image super-resolution (SISR), VSR can benefit from additional information in the temporal domain. However, this also imposes an additional requirement, as the generated frames need to be consistent along time.

cs.CV↗

arXiv2020

Joint Demosaicing and Super-Resolution (JDSR): Network Design and Perceptual Optimization

Image demosaicing and super-resolution are two important tasks in color imaging pipeline. So far they have been mostly independently studied in the open literature of deep learning; little is known about the potential benefit of formulating a joint demosaicing and super-resolution (JDSR) problem. In this paper, we propose an end-to-end optimization solution to the JDSR problem and demonstrate its practical significance in computational imaging. Our technical contributions are mainly two-fold. On network design, we have developed a Residual-Dense Squeeze-and-Excitation Networks (RDSEN) supported by a pre-demosaicing network (PDNet) as the pre-processing step. We address the issue of spatio-spectral attention for color-filter-array (CFA) data and discuss how to achieve better information flow by concatenating Residue-Dense Squeeze-and-Excitation Blocks (RDSEBs) for JDSR. Experimental results have shown that significant PSNR/SSIM gain can be achieved by RDSEN over previous network architectures including state-of-the-art RCAN. On perceptual optimization, we propose to leverage the latest ideas including relativistic discriminator and pre-excitation perceptual loss function to further improve the visual quality of textured regions in reconstructed images. Our extensive experiment results have shown that Texture-enhanced Relativistic average Generative Adversarial Network (TRaGAN) can produce both subjectively more pleasant images and objectively lower perceptual distortion scores than standard GAN for JDSR. Finally, we have verified the benefit of JDSR to high-quality image reconstruction from real-world Bayer pattern data collected by NASA Mars Curiosity.

eess.IV↗

arXiv2018

Hydrogen Decrepitation and Spark Plasma Sintering to Produce Recycled SmCo5 Magnets With High Coercivity

Spark plasma sintering (SPS) technique is applied in combination with hydrogen decrepitation process for the recycling of SmCo5 magnets. The SmCo5 magnets for recycling were first decrepitated by hydrogen gas of a pressure of 4 bar for 3 hours to produce decrepitated powder. This powder was then used to prepare isotropic sintered magnets using the SPS technique, by sintering at 800-1000 oC for 1 minute. Full densification of the SPS-ed magnets was possible at a temperature of 1000 oC. The sample sintered at 900 oC showed the best internal coercivity (jHc) of higher than 1500 kA/m with high remanence (Br) value of 0.47 T and energy product (BH(max)) of 43.4 kJ/m3. The properties of the SPS-ed sample sintered at 900 oC were compared with conventionally sintered (CVS-ed) sample prepared by using fresh SmCo5 powder. The results showed the improvement of the magnetic properties of the SPS-ed sample in comparison to the CVS-ed sample at room temperature, and the possibility to use the SPS-ed sample at high temperature of 180 oC, where the sample showed good magnetic properties of jHc of 1502 kA/m, Br of 0.44 T and BH(max) of 36.4 kJ/m3. The microstructure and X-ray diffraction patterns of the SPS-ed and the CVS-ed samples were studied; where the samples showed to basically consist of SmCo5 matrix phase with Sm2Co7 and Sm-oxides.

cond-mat.mtrl-sci↗