Perceptually Optimized Super Resolution

• URL: http://arxiv.org/abs/2411.17513v1
• Date: Tue, 26 Nov 2024 15:24:45 GMT
• Title: Perceptually Optimized Super Resolution
• Authors: Volodymyr Karpenko, Taimoor Tariq, Jorge Condor, Piotr Didyk,
• Abstract summary: We propose a perceptually inspired and architecture-agnostic approach for controlling the visual quality and efficiency of super-resolution techniques. The core is a perceptual model that dynamically guides super-resolution methods according to the human's sensitivity to image details. We demonstrate the application of our proposed model in combination with network branching, and network complexity reduction to improve the computational efficiency of super-resolution methods without visible quality loss.
• Score: 7.728090438152828
• License:
• Abstract: Modern deep-learning based super-resolution techniques process images and videos independently of the underlying content and viewing conditions. However, the sensitivity of the human visual system to image details changes depending on the underlying content characteristics, such as spatial frequency, luminance, color, contrast, or motion. This observation hints that computational resources spent on up-sampling visual content may be wasted whenever a viewer cannot resolve the results. Motivated by this observation, we propose a perceptually inspired and architecture-agnostic approach for controlling the visual quality and efficiency of super-resolution techniques. The core is a perceptual model that dynamically guides super-resolution methods according to the human's sensitivity to image details. Our technique leverages the limitations of the human visual system to improve the efficiency of super-resolution techniques by focusing computational resources on perceptually important regions; judged on the basis of factors such as adapting luminance, contrast, spatial frequency, motion, and viewing conditions. We demonstrate the application of our proposed model in combination with network branching, and network complexity reduction to improve the computational efficiency of super-resolution methods without visible quality loss. Quantitative and qualitative evaluations, including user studies, demonstrate the effectiveness of our approach in reducing FLOPS by factors of 2$\mathbf{x}$ and greater, without sacrificing perceived quality.

Related papers

• Research on Image Super-Resolution Reconstruction Mechanism based on Convolutional Neural Network [8.739451985459638]
  Super-resolution algorithms transform one or more sets of low-resolution images captured from the same scene into high-resolution images. The extraction of image features and nonlinear mapping methods in the reconstruction process remain challenging for existing algorithms. The objective is to recover high-quality, high-resolution images from low-resolution images.
  arXiv  Detail & Related papers  (2024-07-18T06:50:39Z)
• Efficient Visual State Space Model for Image Deblurring [83.57239834238035]
  Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration. We propose a simple yet effective visual state space model (EVSSM) for image deblurring.
  arXiv  Detail & Related papers  (2024-05-23T09:13:36Z)
• A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models [25.69505971220203]
  Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems. GANs often introduce side effects into the outputs, such as unexpected artifacts and noises. We propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process.
  arXiv  Detail & Related papers  (2024-03-15T17:29:16Z)
• Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques [6.36998581871295]
  Video inpainting is a process that restores or fills in missing or corrupted portions of video sequences with plausible content. Our study deconstructs major techniques, their underpinning theories, and their effective applications. We employ a human-centric approach to assess visual quality, enlisting a panel of annotators to evaluate the output of different video inpainting techniques.
  arXiv  Detail & Related papers  (2024-01-31T14:41:40Z)
• Neural Point-based Volumetric Avatar: Surface-guided Neural Points for Efficient and Photorealistic Volumetric Head Avatar [62.87222308616711]
  We propose fullname (name), a method that adopts the neural point representation and the neural volume rendering process. Specifically, the neural points are strategically constrained around the surface of the target expression via a high-resolution UV displacement map. By design, our name is better equipped to handle topologically changing regions and thin structures while also ensuring accurate expression control when animating avatars.
  arXiv  Detail & Related papers  (2023-07-11T03:40:10Z)
• Textural-Structural Joint Learning for No-Reference Super-Resolution Image Quality Assessment [59.91741119995321]
  We develop a dual stream network to jointly explore the textural and structural information for quality prediction, dubbed TSNet. By mimicking the human vision system (HVS) that pays more attention to the significant areas of the image, we develop the spatial attention mechanism to make the visual-sensitive areas more distinguishable. Experimental results show the proposed TSNet predicts the visual quality more accurate than the state-of-the-art IQA methods, and demonstrates better consistency with the human's perspective.
  arXiv  Detail & Related papers  (2022-05-27T09:20:06Z)
• Learning GAN-based Foveated Reconstruction to Recover Perceptually Important Image Features [0.0]
  We consider the problem of efficiently guiding the training of foveated reconstruction techniques. Our primary goal is to make the training procedure less sensitive to distortions that humans cannot detect. Our evaluations revealed significant improvements in the perceived image reconstruction quality compared with the standard GAN-based training approach.
  arXiv  Detail & Related papers  (2021-08-07T18:39:49Z)
• Analysis and evaluation of Deep Learning based Super-Resolution algorithms to improve performance in Low-Resolution Face Recognition [0.0]
  Super-resolution algorithms may be able to recover the discriminant properties of the subjects involved. This project aimed at evaluating and adapting different deep neural network architectures for the task of face super-resolution. Experiments showed that general super-resolution architectures might enhance face verification performance of deep neural networks trained on high-resolution faces.
  arXiv  Detail & Related papers  (2021-01-19T02:41:57Z)
• Deep Learning-based Face Super-resolution: A Survey [78.11274281686246]
  Face super-resolution, also known as face hallucination, is a domain-specific image super-resolution problem. To date, few summaries of the studies on the deep learning-based face super-resolution are available. In this survey, we present a comprehensive review of deep learning techniques in face super-resolution in a systematic manner.
  arXiv  Detail & Related papers  (2021-01-11T08:17:11Z)
• Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution [89.1947690981471]
  We propose a purposeful and interpretable detail-fidelity attention network to progressively process smoothes and details in divide-and-conquer manner. Particularly, we propose a Hessian filtering for interpretable feature representation which is high-profile for detail inference. Experiments demonstrate that the proposed methods achieve superior performances over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-09-28T08:31:23Z)
• Gated Fusion Network for Degraded Image Super Resolution [78.67168802945069]
  We propose a dual-branch convolutional neural network to extract base features and recovered features separately. By decomposing the feature extraction step into two task-independent streams, the dual-branch model can facilitate the training process.
  arXiv  Detail & Related papers  (2020-03-02T13:28:32Z)

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.