A very deep convolutional neural network (CNN) has recently achieved great success for image super-resolution (SR) and offered hierarchical features as well. However, most deep CNN based SR models do not make full use of the hierarchical features from the original low-resolution (LR) images, thereby achieving relatively-low performance. In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via dense connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory (CM) mechanism. Local feature fusion in RDB is then used to adaptively learn more effective features from preceding and current local features and stabilizes the training of wider network. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. Extensive experiments on benchmark datasets with different degradation models show that our RDN achieves favorable performance against state-of-the-art methods.
Despite that convolutional neural networks (CNN) have recently demonstrated high-quality reconstruction for single-image super-resolution (SR), recovering natural and realistic texture remains a challenging problem. In this paper, we show that it is possible to recover textures faithful to semantic classes. In particular, we only need to modulate features of a few intermediate layers in a single network conditioned on semantic segmentation probability maps. This is made possible through a novel Spatial Feature Transform (SFT) layer that generates affine transformation parameters for spatial-wise feature modulation. SFT layers can be trained end-to-end together with the SR network using the same loss function. During testing, it accepts an input image of arbitrary size and generates a high-resolution image with just a single forward pass conditioned on the categorical priors. Our final results show that an SR network equipped with SFT can generate more realistic and visually pleasing textures in comparison to state-of-the-art SRGAN and EnhanceNet.
The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has been adopted to address this issue. But it suffers from gridding effect, and the resulting receptive field is only a sparse sampling of input image with checkerboard patterns. In this paper, we present a novel multi-level wavelet CNN (MWCNN) model for better tradeoff between receptive field size and computational efficiency. With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork. Furthermore, another convolutional layer is further used to decrease the channels of feature maps. In the expanding subnetwork, inverse wavelet transform is then deployed to reconstruct the high resolution feature maps. Our MWCNN can also be explained as the generalization of dilated filtering and subsampling, and can be applied to many image restoration tasks. The experimental results clearly show the effectiveness of MWCNN for image denoising, single image super-resolution, and JPEG image artifacts removal.
Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Moreover, they lack scalability in learning a single model to non-blindly deal with multiple degradations. To address these issues, we propose a general framework with dimensionality stretching strategy that enables a single convolutional super-resolution network to take two key factors of the SISR degradation process, i.e., blur kernel and noise level, as input. Consequently, the super-resolver can handle multiple and even spatially variant degradations, which significantly improves the practicability. Extensive experimental results on synthetic and real LR images show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.
Many classic methods have shown non-local self-similarity in natural images to be an effective prior for image restoration. However, it remains unclear and challenging to make use of this intrinsic property via deep networks. In this paper, we propose a non-local recurrent network (NLRN) as the first attempt to incorporate non-local operations into a recurrent neural network (RNN) for image restoration. The main contributions of this work are: (1) Unlike existing methods that measure self-similarity in an isolated manner, the proposed non-local module can be flexibly integrated into existing deep networks for end-to-end training to capture deep feature correlation between each location and its neighborhood. (2) We fully employ the RNN structure for its parameter efficiency and allow deep feature correlation to be propagated along adjacent recurrent states. This new design boosts robustness against inaccurate correlation estimation due to severely degraded images. (3) We show that it is essential to maintain a confined neighborhood for computing deep feature correlation given degraded images. This is in contrast to existing practice that deploys the whole image. Extensive experiments on both image denoising and super-resolution tasks are conducted. Thanks to the recurrent non-local operations and correlation propagation, the proposed NLRN achieves superior results to state-of-the-art methods with much fewer parameters.
Many inverse problems involve two or more sets of variables that represent different physical quantities but are tightly coupled with each other. For example, image super-resolution requires joint estimation of the image and motion parameters from noisy measurements. Exploiting this structure is key for efficiently solving these large-scale optimization problems, which are often ill-conditioned. In this paper, we present a new method called Linearize And Project (LAP) that offers a flexible framework for solving inverse problems with coupled variables. LAP is most promising for cases when the subproblem corresponding to one of the variables is considerably easier to solve than the other. LAP is based on a Gauss-Newton method, and thus after linearizing the residual, it eliminates one block of variables through projection. Due to the linearization, this block can be chosen freely. Further, LAP supports direct, iterative, and hybrid regularization as well as constraints. Therefore LAP is attractive, e.g., for ill-posed imaging problems. These traits differentiate LAP from common alternatives for this type of problem such as variable projection (VarPro) and block coordinate descent (BCD). Our numerical experiments compare the performance of LAP to BCD and VarPro using three coupled problems whose forward operators are linear with respect to one block and nonlinear for the other set of variables.
This work identifies and addresses two important technical challenges in single-image super-resolution: (1) how to upsample an image without magnifying noise and (2) how to preserve large scale structure when upsampling. We summarize the techniques we developed for our second place entry in Track 1 (Bicubic Downsampling), seventh place entry in Track 2 (Realistic Adverse Conditions), and seventh place entry in Track 3 (Realistic difficult) in the 2018 NTIRE Super-Resolution Challenge. Furthermore, we present new neural network architectures that specifically address the two challenges listed above: denoising and preservation of large-scale structure.
VQGAN으로 사전학습된 이산 특징 코드북(HR prior)을 활용해, 저해상도 이미지의 특징을 왜곡 없는 고해상도 대응 특징에 매칭하는 FeMaSR 프레임워크를 제안한다. 불안정한 GAN 학습이나 명시적 참조 이미지 없이도, 의미론적 정규화와 잔차 단축 연결을 통해 기존 방법 대비 더 사실적인 초고해상도 이미지를 생성함을 실험으로 검증했다.
이 논문은 CVPR 2025에서 개최되는 제10회 NTIRE 워크샵의 연계 경진대회 중 하나인 NTIRE 2025 이미지 초해상도($\times$4) 챌린지를 소개합니다. 이 챌린지의 목표는 $\times$4 배율의 바이큐빅 다운샘플링(bicubic downsampling)을 통해 생성된 저해상도(LR) 이미지로부터 고해상도(HR) 이미지를 복원하는 것입니다. 그 목적은 최첨단 SR 성능을 달성하는 효과적인 네트워크 설계 또는 솔루션을 개발하는 데 있습니다. 이미지 SR 연구의 이중적인 목표를 반영하기 위해 본 챌린지는 두 개의 하위 트랙으로 구성됩니다: (1) 픽셀 단위 정확도를 강조하고 PSNR을 기준으로 제출물을 순위 매기는 복원(restoration) 트랙, (2) 시각적 사실감에 초점을 맞추고 지각적 점수(perceptual score)로 결과를 순위 매기는 지각(perceptual) 트랙입니다. 총 286명의 참가자가 경진대회에 등록하였고, 25개 팀이 유효한 결과물을 제출했습니다. 본 보고서는 챌린지 설계, 데이터셋, 평가 프로토콜, 주요 결과 및 각 팀의 방법론을 요약합니다. 이 챌린지는 최첨단 기술을 발전시키고 이미지 초해상도 분야의 진전을 도모하는 벤치마크 역할을 합니다.
이 논문은 이미지 초해상도($\times$4)에 관한 NTIRE 2024 챌린지를 검토하고, 제안된 해결책과 도출된 결과를 조명합니다. 이 챌린지는 사전 정보를 활용하여 저해상도(LR) 입력으로부터 4배 확대된 대응하는 고해상도(HR) 이미지를 생성하는 과정을 포함합니다. LR 이미지는 바이큐빅 다운샘플링에 의한 열화에서 비롯됩니다. 이 챌린지의 목적은 연산 자원(예: 모델 크기 및 FLOPs)이나 학습 데이터에 대한 제약 없이 최고 수준의 초해상도(SR) 성능을 보여주는 설계나 솔루션을 도출하는 것입니다. 해당 챌린지 트랙은 DIV2K 테스트 데이터셋에서 PSNR 지표를 사용하여 성능을 평가합니다. 이번 대회에는 199명이 등록하였고, 그중 20개 팀이 유효한 결과물을 제출했습니다. 이러한 집단적 노력은 단일 이미지 초해상도의 성능 경계를 확장할 뿐만 아니라, 이 분야의 최신 동향에 대한 포괄적인 개요를 제공합니다.