Invertible Residual Rescaling Models
- URL: http://arxiv.org/abs/2405.02945v2
- Date: Sun, 12 May 2024 18:37:34 GMT
- Title: Invertible Residual Rescaling Models
- Authors: Jinmin Li, Tao Dai, Yaohua Zha, Yilu Luo, Longfei Lu, Bin Chen, Zhi Wang, Shu-Tao Xia, Jingyun Zhang,
- Abstract summary: Invertible Rescaling Networks (IRNs) and their variants have witnessed remarkable achievements in various image processing tasks like image rescaling.
We propose Invertible Residual Rescaling Models (IRRM) for image rescaling by learning a bijection between a high-resolution image and its low-resolution counterpart with a specific distribution.
Our IRRM has respectively PSNR gains of at least 0.3 dB over HCFlow and IRN in the x4 rescaling while only using 60% parameters and 50% FLOPs.
- Score: 46.28263683643467
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Invertible Rescaling Networks (IRNs) and their variants have witnessed remarkable achievements in various image processing tasks like image rescaling. However, we observe that IRNs with deeper networks are difficult to train, thus hindering the representational ability of IRNs. To address this issue, we propose Invertible Residual Rescaling Models (IRRM) for image rescaling by learning a bijection between a high-resolution image and its low-resolution counterpart with a specific distribution. Specifically, we propose IRRM to build a deep network, which contains several Residual Downscaling Modules (RDMs) with long skip connections. Each RDM consists of several Invertible Residual Blocks (IRBs) with short connections. In this way, RDM allows rich low-frequency information to be bypassed by skip connections and forces models to focus on extracting high-frequency information from the image. Extensive experiments show that our IRRM performs significantly better than other state-of-the-art methods with much fewer parameters and complexity. Particularly, our IRRM has respectively PSNR gains of at least 0.3 dB over HCFlow and IRN in the x4 rescaling while only using 60% parameters and 50% FLOPs. The code will be available at https://github.com/THU-Kingmin/IRRM.
Related papers
- NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
This paper proposes to directly modulate the generation process of diffusion models using fMRI signals.
By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
arXiv Detail & Related papers (2024-03-27T02:42:52Z) - Compound Attention and Neighbor Matching Network for Multi-contrast MRI
Super-resolution [7.197850827700436]
Multi-contrast super-resolution of MRI can achieve better results than single-image super-resolution.
We propose a novel network architecture with compound-attention and neighbor matching (CANM-Net) for multi-contrast MRI SR.
CANM-Net outperforms state-of-the-art approaches in both retrospective and prospective experiments.
arXiv Detail & Related papers (2023-07-05T09:44:02Z) - DiffIR: Efficient Diffusion Model for Image Restoration [108.82579440308267]
Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network.
Traditional DMs running massive iterations on a large model to estimate whole images or feature maps is inefficient for image restoration.
We propose DiffIR, which consists of a compact IR prior extraction network (CPEN), dynamic IR transformer (DIRformer), and denoising network.
arXiv Detail & Related papers (2023-03-16T16:47:14Z) - Model-Guided Multi-Contrast Deep Unfolding Network for MRI
Super-resolution Reconstruction [68.80715727288514]
We show how to unfold an iterative MGDUN algorithm into a novel model-guided deep unfolding network by taking the MRI observation matrix.
In this paper, we propose a novel Model-Guided interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction.
arXiv Detail & Related papers (2022-09-15T03:58:30Z) - An Arbitrary Scale Super-Resolution Approach for 3-Dimensional Magnetic
Resonance Image using Implicit Neural Representation [37.43985628701494]
High Resolution (HR) medical images provide rich anatomical structure details to facilitate early and accurate diagnosis.
Recent studies showed that, with deep convolutional neural networks, isotropic HR MR images could be recovered from low-resolution (LR) input.
We propose ArSSR, an Arbitrary Scale Super-Resolution approach for recovering 3D HR MR images.
arXiv Detail & Related papers (2021-10-27T14:48:54Z) - Multimodal-Boost: Multimodal Medical Image Super-Resolution using
Multi-Attention Network with Wavelet Transform [5.416279158834623]
Loss of corresponding image resolution degrades the overall performance of medical image diagnosis.
Deep learning based single image super resolution (SISR) algorithms has revolutionized the overall diagnosis framework.
This work proposes generative adversarial network (GAN) with deep multi-attention modules to learn high-frequency information from low-frequency data.
arXiv Detail & Related papers (2021-10-22T10:13:46Z) - Over-and-Under Complete Convolutional RNN for MRI Reconstruction [57.95363471940937]
Recent deep learning-based methods for MR image reconstruction usually leverage a generic auto-encoder architecture.
We propose an Over-and-Under Complete Convolu?tional Recurrent Neural Network (OUCR), which consists of an overcomplete and an undercomplete Convolutional Recurrent Neural Network(CRNN)
The proposed method achieves significant improvements over the compressed sensing and popular deep learning-based methods with less number of trainable parameters.
arXiv Detail & Related papers (2021-06-16T15:56:34Z) - MDCN: Multi-scale Dense Cross Network for Image Super-Resolution [35.59973281360541]
We propose a Multi-scale Dense Cross Network (MDCN), which achieves great performance with fewer parameters and less execution time.
MDCN consists of multi-scale dense cross blocks (MDCBs), hierarchical feature distillation block (HFDB), and dynamic reconstruction block (DRB)
arXiv Detail & Related papers (2020-08-30T03:50:19Z) - Cross-Scale Internal Graph Neural Network for Image Super-Resolution [147.77050877373674]
Non-local self-similarity in natural images has been well studied as an effective prior in image restoration.
For single image super-resolution (SISR), most existing deep non-local methods only exploit similar patches within the same scale of the low-resolution (LR) input image.
This is achieved using a novel cross-scale internal graph neural network (IGNN)
arXiv Detail & Related papers (2020-06-30T10:48:40Z)
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.