Deep Back-Projection Networks for Super-Resolution

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

et al. 2019

Deep learning based image Super-Resolution (SR) has shown rapid development due to its ability of big data digestion. Generally, deeper and wider networks can extract richer feature maps and generate SR images with remarkable quality. However, the more complex network we have, the more time consumption is required for practical applications. It is important to have a simplified network for efficient image SR. In this paper, we propose an Attention based Back Projection Network (ABPN) for image superresolution. Similar to some recent works, we believe that the back projection mechanism can be further developed for SR. Enhanced back projection blocks are suggested to iteratively update low-and high-resolution feature residues. Inspired by recent studies on attention models, we propose a Spatial Attention Block (SAB) to learn the cross-correlation across features at different layers. Based on the assumption that a good SR image should be close to the original LR image after down-sampling. We propose a Refined Back Projection Block (RBPB) for final reconstruction. Extensive experiments on some public and AIM2019 Image Super-Resolution Challenge [4] datasets show that the proposed ABPN can provide state-of-the-art or even better performance in both quantitative and qualitative measurements.

Section: Related Workmentioning

confidence: 99%

“…The Back Projection block was first proposed in DBPN [11] and the further modified version is formed in HBPN [20]. Let us see Figure 3, the idea of back projection is based on the assumption that a good SR image should have an estimated LR image that is as close as possible to the original LR image.…”

Section: Back Projection Blocks For Image Srmentioning

confidence: 99%

Image Super-Resolution via Attention Based Back Projection Networks

Liu

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

et al. 2019

“…This dataset enables researchers to train deeper and wider networks which leads to various development of SR methods. The most advanced SISR networks, such as EDSR [14], DBPN [5] and RCAN [27], have far better training performance on this dataset than previous networks.…”

Section: Single Image Super-resolutionmentioning

confidence: 93%

“…We compare our DNLN with several state-of-theart SISR and VSR methods: DBPN [5], RCAN [27], VESPCN [1], TOFlow [26], FRVSR [18], DUF [8] and RBPN [6]. Note that most previous methods are trained with different datasets and we just compare with the results they provided.…”

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

Deformable Non-Local Network for Video Super-Resolution

Liu

et al. 2019

IEEE Access

The video super-resolution (VSR) task aims to restore a high-resolution video frame by using its corresponding low-resolution frame and multiple neighboring frames. At present, many deep learning-based VSR methods rely on optical flow to perform frame alignment. The final recovery results will be greatly affected by the accuracy of optical flow. However, optical flow estimation cannot be completely accurate, and there are always some errors. In this paper, we propose a novel deformable non-local network (DNLN) which is non-flow-based. Specifically, we apply the improved deformable convolution in our alignment module to achieve adaptive frame alignment at the feature level. Furthermore, we utilize a non-local module to capture the global correlation between the reference frame and aligned neighboring frame, and simultaneously enhance desired fine details in the aligned frame. To reconstruct the final high-quality HR video frames, we use residual in residual dense blocks to take full advantage of the hierarchical features. Experimental results on several datasets demonstrate that the proposed DNLN can achieve state of the art performance on video super-resolution task.

“…To obtain HR image with more delicate details, plenty of algorithms [6,7,8,9,10,11,12,13,14] are proposed and achieve promising results. Especially in the last half decade, the development of deep neural networks leads to a tremendous leap in this field.…”

Section: Introductionmentioning

confidence: 99%

Pixel-Level Self-Paced Learning For Super-Resolution

Lin

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

et al. 2020

Recently, lots of deep networks are proposed to improve the quality of predicted super-resolution (SR) images, due to its widespread use in several image-based fields. However, with these networks being constructed deeper and deeper, they also cost much longer time for training, which may guide the learners to local optimization. To tackle this problem, this paper designs a training strategy named Pixel-level Self-Paced Learning (PSPL) to accelerate the convergence velocity of SISR models. PSPL imitating self-paced learning gives each pixel in the predicted SR image and its corresponding pixel in ground truth an attention weight, to guide the model to a better region in parameter space. Extensive experiments proved that PSPL could speed up the training of SISR models, and prompt several existing models to obtain new better results. Furthermore, the source code is available at https://github.com/Elin24/PSPL Index Termssuper-resolution, training strategy, selfpaced learning * Qi Wang is the corresponding author.