SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom

• URL: http://arxiv.org/abs/2104.00848v1
• Date: Fri, 2 Apr 2021 01:58:00 GMT
• Title: SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom
• Authors: Kangfu Mei, Shenglong Ye, Rui Huang
• Abstract summary: Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. These algorithms often yield significant artifacts when dealing with real-world super-resolution problems. We introduce a Squared Deformable Alignment Network (SDAN) to address this issue.
• Score: 5.202871995038932
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. However, these algorithms often yield significant artifacts when dealing with real-world super-resolution problems due to the difficulty in learning misaligned optical zoom. In this paper, we introduce a Squared Deformable Alignment Network (SDAN) to address this issue. Our network learns squared per-point offsets for convolutional kernels, and then aligns features in corrected convolutional windows based on the offsets. So the misalignment will be minimized by the extracted aligned features. Different from the per-point offsets used in the vanilla Deformable Convolutional Network (DCN), our proposed squared offsets not only accelerate the offset learning but also improve the generation quality with fewer parameters. Besides, we further propose an efficient cross packing attention layer to boost the accuracy of the learned offsets. It leverages the packing and unpacking operations to enlarge the receptive field of the offset learning and to enhance the ability of extracting the spatial connection between the low-resolution images and the referenced images. Comprehensive experiments show the superiority of our method over other state-of-the-art methods in both computational efficiency and realistic details.

Related papers

• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• Learning Weighting Map for Bit-Depth Expansion within a Rational Range [64.15915577164894]
  Bit-depth expansion (BDE) is one of the emerging technologies to display high bit-depth (HBD) image from low bit-depth (LBD) source. Existing BDE methods have no unified solution for various BDE situations. We design a bit restoration network (BRNet) to learn a weight for each pixel, which indicates the ratio of the replenished value within a rational range.
  arXiv  Detail & Related papers  (2022-04-26T02:27:39Z)
• FSOINet: Feature-Space Optimization-Inspired Network for Image Compressive Sensing [11.352530132548912]
  We propose the idea of achieving information flow phase by phase in feature space and design a Feature-Space Optimization-Inspired Network (dubbed FSOINet) Experiments show that the proposed FSOINet outperforms the existing state-of-the-art methods by a large margin both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2022-04-12T03:30:22Z)
• Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment [50.13230641857892]
  We propose a new deep learning framework for the low-light image enhancement (LIE) problem. The proposed framework contains a decomposition network inspired by algorithm unrolling, and adjustment networks considering both global brightness and local brightness sensitivity. Experiments on a series of typical LIE datasets demonstrated the effectiveness of the proposed method, both quantitatively and visually, as compared with existing methods.
  arXiv  Detail & Related papers  (2022-02-12T03:59:38Z)
• Asymmetric CNN for image super-resolution [102.96131810686231]
  Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. We propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a mem?ory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution. Our ACNet can effectively address single image super-resolution (SISR), blind SISR and blind SISR of blind noise problems.
  arXiv  Detail & Related papers  (2021-03-25T07:10:46Z)
• Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications [78.63280020581662]
  A novel convolutional neural network (CNN)-based framework is developed for light field reconstruction from a sparse set of views. We demonstrate the high performance and robustness of the proposed framework compared with state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-03-24T08:16:32Z)
• An Empirical Method to Quantify the Peripheral Performance Degradation in Deep Networks [18.808132632482103]
  convolutional neural network (CNN) kernels compound with each convolutional layer. Deeper and deeper networks combined with stride-based down-sampling means that the propagation of this region can end up covering a non-negligable portion of the image. Our dataset is constructed by inserting objects into high resolution backgrounds, thereby allowing us to crop sub-images which place target objects at specific locations relative to the image border. By probing the behaviour of Mask R-CNN across a selection of target locations, we see clear patterns of performance degredation near the image boundary, and in particular in the image corners.
  arXiv  Detail & Related papers  (2020-12-04T18:00:47Z)
• Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment [33.945579916184364]
  An adaptive fractional dilated convolution (AFDC) is developed to tackle this issue in convolutional kernel level. We provide a concise formulation for mini-batch training and utilize a grouping strategy to reduce computational overhead. Our experimental results demonstrate that our proposed method achieves state-of-the-art performance on image aesthetics assessment over the AVA dataset.
  arXiv  Detail & Related papers  (2020-04-06T21:56:29Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)
• Adaptive Loss Function for Super Resolution Neural Networks Using Convex Optimization Techniques [24.582559317893274]
  Single Image Super-Resolution (SISR) task refers to learn a mapping from low-resolution images to the corresponding high-resolution ones. CNNs are encouraged to learn high-frequency components of the images as well as low-frequency components. We have shown that the proposed method can recover fine details of the images and it is stable in the training process.
  arXiv  Detail & Related papers  (2020-01-21T20:31:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.