HST: Hierarchical Swin Transformer for Compressed Image Super-resolution

• URL: http://arxiv.org/abs/2208.09885v1
• Date: Sun, 21 Aug 2022 13:41:51 GMT
• Title: HST: Hierarchical Swin Transformer for Compressed Image Super-resolution
• Authors: Bingchen Li, Xin Li, Yiting Lu, Sen Liu, Ruoyu Feng, Zhibo Chen
• Abstract summary: We propose the Hierarchical Swin Transformer (HST) network to restore the low-resolution compressed image. Our HST achieves the fifth place in AIM 2022 challenge on the low-quality compressed image super-resolution track, with the PSNR of 23.51dB.
• Score: 26.589370745694502
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts. Since the complex hybrid distortions, it is hard to restore the distorted image with the simple cooperation of super-resolution and compression artifacts removing. In this paper, we take a step forward to propose the Hierarchical Swin Transformer (HST) network to restore the low-resolution compressed image, which jointly captures the hierarchical feature representations and enhances each-scale representation with Swin transformer, respectively. Moreover, we find that the pretraining with Super-resolution (SR) task is vital in compressed image super-resolution. To explore the effects of different SR pretraining, we take the commonly-used SR tasks (e.g., bicubic and different real super-resolution simulations) as our pretraining tasks, and reveal that SR plays an irreplaceable role in the compressed image super-resolution. With the cooperation of HST and pre-training, our HST achieves the fifth place in AIM 2022 challenge on the low-quality compressed image super-resolution track, with the PSNR of 23.51dB. Extensive experiments and ablation studies have validated the effectiveness of our proposed methods.

Related papers

• FIPER: Generalizable Factorized Fields for Joint Image Compression and Super-Resolution [12.77409981295186]
  We propose a unified representation for Super-Resolution (SR) and Image Compression, termed **Factorized Fields**, motivated by the shared principles between these two tasks. We first derive our SR model, which includes a Coefficient Backbone and Basis Swin Transformer for generalizable Factorized Fields. We then leverage the strong information-recovery capabilities of the trained SR modules as priors in the compression pipeline, improving both compression efficiency and detail reconstruction.
  arXiv  Detail & Related papers  (2024-10-23T17:59:57Z)
• 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)
• Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling [6.861753163565238]
  In real-world applications, most images are compressed for transmission. We propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling.
  arXiv  Detail & Related papers  (2023-03-04T08:33:46Z)
• Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration [71.6879432974126]
  In this paper, we explore the novel Swin Transformer V2, to improve SwinIR for image super-resolution. We conduct experiments on three representative tasks: JPEG compression artifacts removal, image super-resolution (classical and lightweight), and compressed image super-resolution. Experimental results demonstrate that our method, Swin2SR, can improve the training convergence and performance of SwinIR.
  arXiv  Detail & Related papers  (2022-09-22T23:25:08Z)
• Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution [64.15915577164894]
  A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing. HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
  arXiv  Detail & Related papers  (2022-06-07T14:55:32Z)
• Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution [64.54162195322246]
  Convolutional neural network (CNN) has achieved great success on image super-resolution (SR) Most deep CNN-based SR models take massive computations to obtain high performance. We propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task.
  arXiv  Detail & Related papers  (2022-03-16T20:10:41Z)
• SwinIR: Image Restoration Using Swin Transformer [124.8794221439392]
  We propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. We conduct experiments on three representative tasks: image super-resolution, image denoising and JPEG compression artifact reduction.
  arXiv  Detail & Related papers  (2021-08-23T15:55:32Z)
• SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation [65.88321755969677]
  Deep CNNs have achieved significant successes in image processing and its applications, including single image super-resolution. Recent approaches extend the scope to real-valued upsampling factors. We propose the SRWarp framework to further generalize the SR tasks toward an arbitrary image transformation.
  arXiv  Detail & Related papers  (2021-04-21T02:50:41Z)

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.