CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task

• URL: http://arxiv.org/abs/2404.14132v1
• Date: Mon, 22 Apr 2024 12:33:18 GMT
• Title: CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task
• Authors: Kangzhen Yang, Tao Hu, Kexin Dai, Genggeng Chen, Yu Cao, Wei Dong, Peng Wu, Yanning Zhang, Qingsen Yan,
• Abstract summary: Composite Refinement Network (CRNet) can perform unified image restoration and enhancement. CRNet explicitly separates and strengthens high and low-frequency information through pooling layers. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge.
• Score: 44.14681936953848
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images, researchers have attempted various image restoration and enhancement operations on photographs, including denoising, deblurring, and high dynamic range imaging. However, merely performing a single type of image enhancement still cannot yield satisfactory images. In this paper, to deal with the challenge above, we propose the Composite Refinement Network (CRNet) to address this issue using multiple exposure images. By fully integrating information-rich multiple exposure inputs, CRNet can perform unified image restoration and enhancement. To improve the quality of image details, CRNet explicitly separates and strengthens high and low-frequency information through pooling layers, using specially designed Multi-Branch Blocks for effective fusion of these frequencies. To increase the receptive field and fully integrate input features, CRNet employs the High-Frequency Enhancement Module, which includes large kernel convolutions and an inverted bottleneck ConvFFN. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge, surpassing previous SOTA models in both testing metrics and visual quality.

Related papers

• Exposure Bracketing is All You Need for Unifying Image Restoration and Enhancement Tasks [50.822601495422916]
  We propose to utilize exposure bracketing photography to unify image restoration and enhancement tasks. Due to the difficulty in collecting real-world pairs, we suggest a solution that first pre-trains the model with synthetic paired data. In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed.
  arXiv  Detail & Related papers  (2024-01-01T14:14:35Z)
• A Mountain-Shaped Single-Stage Network for Accurate Image Restoration [9.431709365739462]
  In image restoration, it is typically necessary to maintain a complex balance between spatial details and contextual information. We propose a single-stage design base on a simple U-Net architecture, which removes or replaces unnecessary nonlinear activation functions. Our approach, named as M3SNet, outperforms previous state-of-the-art models while using less than half the computational costs.
  arXiv  Detail & Related papers  (2023-05-09T03:18:35Z)
• Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement [75.25451566988565]
  We propose a novel Gated Multi-Resolution Transfer Network (GMTNet) to reconstruct a spatially precise high-quality image from a burst of low-quality raw images. Detailed experimental analysis on five datasets validates our approach and sets a state-of-the-art for burst super-resolution, burst denoising, and low-light burst enhancement.
  arXiv  Detail & Related papers  (2023-04-13T17:54:00Z)
• Learning Enriched Features for Fast Image Restoration and Enhancement [166.17296369600774]
  This paper presents a holistic goal of maintaining spatially-precise high-resolution representations through the entire network. We learn an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Our approach achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement.
  arXiv  Detail & Related papers  (2022-04-19T17:59:45Z)
• Del-Net: A Single-Stage Network for Mobile Camera ISP [14.168130234198467]
  Traditional image signal processing (ISP) pipeline in a smartphone camera consists of several image processing steps performed sequentially to reconstruct a high quality sRGB image from the raw sensor data. Deep learning methods using convolutional neural networks (CNN) have become popular in solving many image-related tasks such as image denoising, contrast enhancement, super resolution, deblurring, etc. In this paper we propose DelNet - a single end-to-end deep learning model - to learn the entire ISP pipeline within reasonable complexity for smartphone deployment.
  arXiv  Detail & Related papers  (2021-08-03T16:51:11Z)
• HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization [39.82945546614887]
  We propose a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction. Our method achieves the state-of-the-art performance in quantitative comparisons and visual quality.
  arXiv  Detail & Related papers  (2021-05-27T12:12:34Z)
• Deep Burst Super-Resolution [165.90445859851448]
  We propose a novel architecture for the burst super-resolution task. Our network takes multiple noisy RAW images as input, and generates a denoised, super-resolved RGB image as output. In order to enable training and evaluation on real-world data, we additionally introduce the BurstSR dataset.
  arXiv  Detail & Related papers  (2021-01-26T18:57:21Z)
• Deep Attentive Generative Adversarial Network for Photo-Realistic Image De-Quantization [25.805568996596783]
  De-quantization can improve the visual quality of low bit-depth image to display on high bit-depth screen. This paper proposes DAGAN algorithm to perform super-resolution on image intensity resolution. DenseResAtt module consists of dense residual blocks armed with self-attention mechanism.
  arXiv  Detail & Related papers  (2020-04-07T06:45:01Z)
• Learning Enriched Features for Real Image Restoration and Enhancement [166.17296369600774]
  convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. We present a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network. Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
  arXiv  Detail & Related papers  (2020-03-15T11:04:30Z)

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.