Deformation-Invariant Neural Network and Its Applications in Distorted Image Restoration and Analysis

• URL: http://arxiv.org/abs/2310.02641v2
• Date: Tue, 7 Nov 2023 17:11:59 GMT
• Title: Deformation-Invariant Neural Network and Its Applications in Distorted Image Restoration and Analysis
• Authors: Han Zhang, Qiguang Chen, Lok Ming Lui
• Abstract summary: Images degraded by geometric distortions pose a significant challenge to imaging and computer vision tasks such as object recognition. Deep learning-based imaging models usually fail to give accurate performance for geometrically distorted images. We propose the deformation-invariant neural network (DINN), a framework to address the problem of imaging tasks for geometrically distorted images.
• Score: 8.009077765403287
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Images degraded by geometric distortions pose a significant challenge to imaging and computer vision tasks such as object recognition. Deep learning-based imaging models usually fail to give accurate performance for geometrically distorted images. In this paper, we propose the deformation-invariant neural network (DINN), a framework to address the problem of imaging tasks for geometrically distorted images. The DINN outputs consistent latent features for images that are geometrically distorted but represent the same underlying object or scene. The idea of DINN is to incorporate a simple component, called the quasiconformal transformer network (QCTN), into other existing deep networks for imaging tasks. The QCTN is a deep neural network that outputs a quasiconformal map, which can be used to transform a geometrically distorted image into an improved version that is closer to the distribution of natural or good images. It first outputs a Beltrami coefficient, which measures the quasiconformality of the output deformation map. By controlling the Beltrami coefficient, the local geometric distortion under the quasiconformal mapping can be controlled. The QCTN is lightweight and simple, which can be readily integrated into other existing deep neural networks to enhance their performance. Leveraging our framework, we have developed an image classification network that achieves accurate classification of distorted images. Our proposed framework has been applied to restore geometrically distorted images by atmospheric turbulence and water turbulence. DINN outperforms existing GAN-based restoration methods under these scenarios, demonstrating the effectiveness of the proposed framework. Additionally, we apply our proposed framework to the 1-1 verification of human face images under atmospheric turbulence and achieve satisfactory performance, further demonstrating the efficacy of our approach.

Related papers

• Space-Variant Total Variation boosted by learning techniques in few-view tomographic imaging [0.0]
  This paper focuses on the development of a space-variant regularization model for solving an under-determined linear inverse problem. The primary objective of the proposed model is to achieve a good balance between denoising and the preservation of fine details and edges. A convolutional neural network is designed, to approximate both the ground truth image and its gradient using an elastic loss function in its training.
  arXiv  Detail & Related papers  (2024-04-25T08:58:41Z)
• 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)
• RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning [62.86400614141706]
  We propose a new learning model, i.e., Rectangling Rectification Network (RecRecNet) Our model can flexibly warp the source structure to the target domain and achieves an end-to-end unsupervised deformation. Experiments show the superiority of our solution over the compared methods on both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2023-01-04T15:12:57Z)
• One-Stage Deep Edge Detection Based on Dense-Scale Feature Fusion and Pixel-Level Imbalance Learning [5.370848116287344]
  We propose a one-stage neural network model that can generate high-quality edge images without postprocessing. The proposed model adopts a classic encoder-decoder framework in which a pre-trained neural model is used as the encoder. We propose a new loss function that addresses the pixel-level imbalance in the edge image.
  arXiv  Detail & Related papers  (2022-03-17T15:26:00Z)
• Spatially-Adaptive Image Restoration using Distortion-Guided Networks [51.89245800461537]
  We present a learning-based solution for restoring images suffering from spatially-varying degradations. We propose SPAIR, a network design that harnesses distortion-localization information and dynamically adjusts to difficult regions in the image.
  arXiv  Detail & Related papers  (2021-08-19T11:02:25Z)
• Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces [103.08512487830669]
  This paper presents an uncalibrated deep neural network framework for the photometric stereo problem. Existing neural network-based methods either require exact light directions or ground-truth surface normals of the object or both. We propose an uncalibrated neural inverse rendering approach to this problem.
  arXiv  Detail & Related papers  (2020-12-12T10:33:08Z)
• Generative and Discriminative Learning for Distorted Image Restoration [22.230017059874445]
  Liquify is a technique for image editing, which can be used for image distortion. We propose a novel generative and discriminative learning method based on deep neural networks.
  arXiv  Detail & Related papers  (2020-11-11T14:01:29Z)
• Category Level Object Pose Estimation via Neural Analysis-by-Synthesis [64.14028598360741]
  In this paper we combine a gradient-based fitting procedure with a parametric neural image synthesis module. The image synthesis network is designed to efficiently span the pose configuration space. We experimentally show that the method can recover orientation of objects with high accuracy from 2D images alone.
  arXiv  Detail & Related papers  (2020-08-18T20:30:47Z)
• Learning to Restore a Single Face Image Degraded by Atmospheric Turbulence using CNNs [93.72048616001064]
  Images captured under such condition suffer from a combination of geometric deformation and space varying blur. We present a deep learning-based solution to the problem of restoring a turbulence-degraded face image.
  arXiv  Detail & Related papers  (2020-07-16T15:25:08Z)

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.