Bicubic Downsampling Research Articles

Self-supervised cycle-consistent learning for scale-arbitrary real-world single image super-resolution

Whether conventional machine learning-based or current deep neural networks-based single image super-resolution (SISR) methods, they are generally trained and validated on synthetic datasets, in which low-resolution (LR) inputs are artificially produced by degrading high-resolution (HR) images based on a hand-crafted degradation model (e.g., bicubic downsampling). One of the main reasons for this is that it is challenging to build a realistic dataset composed of real-world LR–HR image pairs. However, a domain gap exists between synthetic and real-world data because the degradations in real scenarios are more complicated, limiting the performance in practical applications of SISR models trained with synthetic data. To address these problems, we propose a Self-supervised Cycle-consistent Learning-based Scale-Arbitrary Super-Resolution framework (SCL-SASR) for real-world images. Inspired by the Maximum a Posteriori estimation, our SCL-SASR consists of a Scale-Arbitrary Super-Resolution Network (SASRN) and an inverse Scale-Arbitrary Resolution-Degradation Network (SARDN). SARDN and SASRN restrain each other with the bidirectional cycle consistency constraints as well as image priors, making SASRN adapt to the image-specific degradation well. Meanwhile, considering the lack of targeted training images and the complexity of realistic degradations, SCL-SASR is designed to be online optimized solely with the LR input prior to the SR reconstruction. Benefitting from the flexible architecture and the self-supervised learning manner, SCL-SASR can easily super-resolve new images with arbitrary integer or non-integer scaling factors. Experiments on real-world images demonstrate the high flexibility and good applicability of SCL-SASR, which achieves better reconstruction performance than state-of-the-art self-supervised learning-based SISR methods as well as several external dataset-trained SISR models.

APPLICATION OF PRE-TRAINED REAL-WORLD SUPER RESOLUTION MODELS TO OPTICAL SATELLITE IMAGE

Abstract. The single image super-resolution (SISR) technique refers to improving the resolution over the original image. In recent years, we use deep learning-based convolutional neural networks to improve the spatial resolution of images more reasonably. To train such deep learning models, we use training samples consisting of the original HR images and LR images obtained by bicubic downsampling. However, this method of training data using downsampling has a negative impact when applying the trained model to real images. That is because the downsampling function that occurs in the real image is unknown, and the hypothetically created LR image does not represent the resolution degradation that can realistically occur. Therefore, SISR methods that use realistic degradation called real-world super-resolution (RWSR) have been proposed. In this paper, we investigate how such RWSR methods using realistic degradation affect the SISR performance of satellite images. The results of applying the trained model to optical satellite images show that the RWSR method is not the most effective way to handle optical satellite images when compared to the deep learning method without modeling the degradation. In particular, we showed that the effect of RWSR with not only upsampling but also noise and blur removal is significant in the visibility of optical satellite images. Moreover, pre-trained RWSR models can be an aid in visually deciphering ground objects.

Weakly-supervised contrastive learning-based implicit degradation modeling for blind image super-resolution

Deep learning-based image super-resolution (SR) methods have attracted growing interest due to their outstanding performance. However, most of these methods assume that the degradations of low-resolution (LR) observations are fixed and known (e.g., bicubic downsampling). This is however not always true in real scenarios. Moreover, the mismatch between the intrinsic degradation of LR images and the assumed degradation generally causes artifacts. Therefore, it is essential to move beyond idealized assumptions and make the SR model adapt to variant degradations. To achieve this goal, we propose a Blind image Super-Resolution approach based on contrastive learning-based Implicit Degradation Modeling (IDMBSR). Since it is challenging to explicitly estimate degradation parameters, a representation is learned from each LR image to model its degradation and differentiate between variant degradations, thereby guiding the subsequent reconstruction to achieve image-specific SR. Since there are no representation labels for LR images, contrastive learning is used to train the attention-enhanced encoder for degradation encoding with the help of degradation parameters for more effective model training. Moreover, to make the reconstruction process adapt to LR images with variant degradations, a degradation-guided SR network is developed, in which the degradation representation adaptively influences the SR process from beginning to end by applying data-driven transformation to middle features. Benefitting from the combination of the degradation representation encoder and the degradation-guided SR network, IDMBSR can adapt to various LR observations without any prior knowledge about their degradations. Experimental results show that IDMBSR outperforms several state-of-the-art blind SR methods with fewer parameters and higher efficiency.

Super-Resolution Reconstruction of 3T-Like Images From 0.35T MRI Using a Hybrid Attention Residual Network

Magnetic resonance (MR) images from low-field scanners present poorer signal-to-noise ratios (SNRs) than those from high-field scanners at the same spatial resolution. To obtain a clinically acceptable SNR, radiologists operating the low-field scanners use a much smaller acquisition matrix than high-field scanners. Thus, the current state of the image quality indicates the need for further research to improve the image quality of low-field systems. Strategies based on super-resolution (SR) techniques can be alternatives for image reconstruction. However, predetermined degradation methods embedded in these techniques, such as bicubic downsampling, seem to impose a performance drop when the actual degradation is different from the pre-defined assumption. In this study, we collected a unique dataset by scanning 70 participants to address this problem. The anatomical locations of the scanned image slices were the same for 0.35T and 3T data. Low-resolution (LR) images (0.35T) and high-resolution (HR) images (3T) were the image pairs used for data training. Herein, we introduce a novel CNN-based network with hybrid attention mechanisms (HybridAttentionResNet, HARN) to adaptively capture diverse information and reconstruct super-resolution 0.35T MR images (3T-like MR images). Specifically, the proposed dense block combines variant dense blocks and attention blocks to extract abundant features from LR images. The experimental results demonstrate that our proposed residual network efficiently recovers significant textures while rendering a high peak signal-to-noise ratio (PSNR) and an appealing structural similarity index (SSIM). Moreover, an extensive subjective-mean-opinion-score (SMOS) proves to be promising in the clinical application using HARN.

Data Acquisition and Preparation for Dual-Reference Deep Learning of Image Super-Resolution.

The performance of deep learning based image super-resolution (SR) methods depend on how accurately the paired low and high resolution images for training characterize the sampling process of real cameras. Low and high resolution (LR ∼ HR) image pairs synthesized by degradation models (e.g., bicubic downsampling) deviate from those in reality; thus the synthetically-trained DCNN SR models work disappointingly when being applied to real-world images. To address this issue, we propose a novel data acquisition process to shoot a large set of LR ∼ HR image pairs using real cameras. The images are displayed on an ultra-high quality screen and captured at different resolutions. The resulting LR ∼ HR image pairs can be aligned at very high sub-pixel precision by a novel spatial-frequency dual-domain registration method, and hence they provide more appropriate training data for the learning task of super-resolution. Moreover, the captured HR image and the original digital image offer dual references to strengthen supervised learning. Experimental results show that training a super-resolution DCNN by our LR ∼ HR dataset achieves higher image quality than training it by other datasets in the literature. Moreover, the proposed screen-capturing data collection process can be automated; it can be carried out for any target camera with ease and low cost, offering a practical way of tailoring the training of a DCNN SR model separately to each of the given cameras.

Toward Real-World Super-Resolution Technique for Fringe Projection Profilometry

Deep learning technique has exhibited promising performance in achieving high-resolution (HR) image from their low-resolution (LR) image in super-resolution (SR) field. However, most of the existing SR methods have two underlying problems. Firstly, degraded datasets (i.e., bicubic downsampling) are usually used to train and evaluate network model, which maybe lead to less effective in practical scenarios. Secondly, 2D-to-3D SR technique is lacking. In this paper, a real-world 2D-to-3D technique is developed to realize SR 3D shape from 2D fringe images in fringe projection profilometry (FPP). A FPP system consisting of one projector and a dual-camera is applied to obtain the real-world dataset where paired LR-HR images on same scene are captured. The 3D geometrical constraints solved from FPP system are employed to align the image pairs by pixel-to-pixel mapping so that more accurate dataset can be obtained. In addition, a flexible multiple-to-two network structure is introduced to achieve SR 3D point cloud from multiple phase-shifting patterns. Experiments demonstrate the comparing between traditional degraded training and our training.

U-Shaped Attention Connection Network for Remote-Sensing Image Super-Resolution

In recent years, deep learning-based remote-sensing image super-resolution (SR) methods have made significant progress, and these methods require a large number of synthetic data for training. To obtain sufficient training data, researchers often generate synthetic data via fixed bicubic downsampling methods. However, the synthesized data cannot reflect the complex degradation process of real remote-sensing images. Thus, performance will dramatically reduce when these methods work in real low-resolution (LR) remote-sensing images. This letter proposes a U-shaped attention connection network (US-ACN) for remote-sensing image SR to solve this issue. Our US-ACN does not rely on any synthetic external dataset for training and merely requires one LR image to complete the training. The US-ACN utilizes remote-sensing images’ strong internal feature repetitiveness and fully learns this internal repetitive feature through a well-designed US-ACN to achieve the remote-sensing image SR. In addition, we design a 3-D attention module to generate effective 3-D weights by modeling channel and spatial attention weights, which is more helpful for the learning of internal features. Through the U-shaped connection among attention modules, context information propagation and attention weights learning are fully utilized. Many experiments show that our US-ACN adequately adapts to the remote-sensing image SR in various situations and performs advanced performance.

Blind Image Super Resolution Using Deep Unsupervised Learning

The goal of single image super resolution (SISR) is to recover a high-resolution (HR) image from a low-resolution (LR) image. Deep learning based methods have recently made a remarkable performance gain in terms of both the effectiveness and efficiency for SISR. Most existing methods have to be trained based on large-scale synthetic paired data in a fully supervised manner. With the available HR natural images, the corresponding LR images are usually synthesized with a simple fixed degradation operation, such as bicubic down-sampling. Then, the learned deep models with these training data usually face difficulty to be generalized to real scenarios with unknown and complicated degradation operations. This study exploits a novel blind image super-resolution framework using a deep unsupervised learning network. The proposed method can simultaneously predict the underlying HR image and its specific degradation operation from the observed LR image only without any prior knowledge. The experimental results on three benchmark datasets validate that our proposed method achieves a promising performance under the unknown degradation models.

Cross-Dimension Attention Guided Self-Supervised Remote Sensing Single-Image Super-Resolution

In recent years, the application of deep learning has achieved a huge leap in the performance of remote sensing image super-resolution (SR). However, most of the existing SR methods employ bicubic downsampling of high-resolution (HR) images to obtain low-resolution (LR) images and use the obtained LR and HR images as training pairs. This supervised method that uses ideal kernel (bicubic) downsampled images to train the network will significantly degrade performance when used in realistic LR remote sensing images, usually resulting in blurry images. The main reason is that the degradation process of real remote sensing images is more complicated. The training data cannot reflect the SR problem of real remote sensing images. Inspired by the self-supervised methods, this paper proposes a cross-dimension attention guided self-supervised remote sensing single-image super-resolution method (CASSISR). It does not require pre-training on a dataset, only utilizes the internal information reproducibility of a single image, and uses the lower-resolution image downsampled from the input image to train the cross-dimension attention network (CDAN). The cross-dimension attention module (CDAM) selectively captures more useful internal duplicate information by modeling the interdependence of channel and spatial features and jointly learning their weights. The proposed CASSISR adapts well to real remote sensing image SR tasks. A large number of experiments show that CASSISR has achieved superior performance to current state-of-the-art methods.

Blind image super-resolution based on prior correction network

Convolutional neural networks (CNNs) based super-resolution (SR) methods have achieved remarkable progress in recent years. Most of these methods assume that the degradation is known and fixed, such as bicubic downsampling. However, the performance of CNNs-based methods suffers from a severe drop when the actual degradation mismatch the training one. This paper proposes a prior correction network (PCNet) to solve the blind SR problem, which makes CNNs-based super-resolvers trained in a fixed blur kernel but applied to other unknown blur kernels. The PCNet consists of a kernel estimation network, a correction filter module, and a correction refinement network. The kernel estimation network aims to estimate unknown blur kernel from the input low-resolution (LR) image. The correction filter module then transfers the estimated degraded domains to adapt to specific degradations (e.g., bicubic downsampling). Finally, the correction refinement network adjusts the corrected LR image to eliminate the influence of blur kernel mismatch or misestimate. Experimental results on diverse datasets show that the proposed PCNet, combined with existing CNNs-based SR methods, outperforms other state-of-the-art algorithms for blind SR. Code is available at: \\url{https://github.com/caoxiang104/PCNet}.

Frequency Consistent Adaptation for Real World Super Resolution

Recent deep-learning based Super-Resolution (SR) methods have achieved remarkable performance on images with known degradation. However, these methods always fail in real-world scene, since the Low-Resolution (LR) images after the ideal degradation (e.g., bicubic down-sampling) deviate from real source domain. The domain gap between the LR images and the real-world images can be observed clearly on frequency density, which inspires us to explicitly narrow the undesired gap caused by incorrect degradation. From this point of view, we design a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying existing SR methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding LR images. To provide useful gradient information for kernel estimation, we propose Frequency Density Comparator (FDC) by distinguishing the frequency density of images on different scales. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models. Extensive experiments show that the proposed FCA improves the performance of the SR model under real-world setting achieving state-of-the-art results with high fidelity and plausible perception, thus providing a novel effective framework for real-world SR application.

Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution

Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolution (RealSR) problem lies in learning feature representations that are both informative and content-aware. In this paper, we propose a Omni-frequency Region-adaptive Network (OR-Net) to address both challenges, here we call features of all low, middle and high frequencies omni-frequency features. Specifically, we start from the frequency perspective and design a Frequency Decomposition (FD) module to separate different frequency components to comprehensively compensate the information lost for real LR image. Then, considering the different regions of real LR image have different frequency information lost, we further design a Region-adaptive Frequency Aggregation (RFA) module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions. The extensive experiments endorse the high-efficient, effective, and scenario-agnostic nature of our OR-Net for RealSR.

Direct Unsupervised Super-Resolution Using Generative Adversarial Network (DUS-GAN) for Real-World Data.

The deep learning models for the Single Image Super-Resolution (SISR) task have found success in recent years. However, one of the prime limitations of existing deep learning-based SISR approaches is that they need supervised training. Specifically, the Low-Resolution (LR) images are obtained through known degradation (for instance, bicubic downsampling) from the High-Resolution (HR) images to provide supervised data as an LR-HR pair. Such training results in a domain shift of learnt models when real-world data is provided with multiple degradation factors not present in the training set. To address this challenge, we propose an unsupervised approach for the SISR task using Generative Adversarial Network (GAN), which we refer to hereafter as DUS-GAN. The novel design of the proposed method accomplishes the SR task without degradation estimation of real-world LR data. In addition, a new human perception-based quality assessment loss, i.e., Mean Opinion Score (MOS), has also been introduced to boost the perceptual quality of SR results. The pertinence of the proposed method is validated with numerous experiments on different reference-based (i.e., NTIRE Real-world SR Challenge validation dataset) and no-reference based (i.e., NTIRE Real-world SR Challenge Track-1 and Track-2) testing datasets. The experimental analysis demonstrates committed improvement from the proposed method over the other state-of-the-art unsupervised SR approaches, both in terms of subjective and quantitative evaluations on different reference metrics (i.e., LPIPS, PI-RMSE graph) and no-reference quality measures such as NIQE, BRISQUE and PIQE. We also provide the implementation of the proposed approach (https://github.com/kalpeshjp89/DUSGAN) to support reproducible research.

Unsupervised Video Satellite Super-Resolution by Using Only a Single Video

Recent studies have shown that deep-learning (DL)-based methods lead to improved performance in video satellite super-resolution (SR). However, the vast majority of prior work is supervised, which is restricted to artificially generated training data (e.g., predetermined bicubic downsampling). Unfortunately, in the real world, the low-resolution (LR) satellite video frames rarely obey these restrictions. To solve this problem, we resort to unsupervised learning and propose a video satellite SR method by using only a single video. The single video SR (SingleVSR) method takes advantage of the power of DL without relying on prior high-resolution (HR) and LR pairs. In the training phase, the LR frames are alternately processed by both downsampling network (i.e., Net <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LR</sub> ) and upsampling network (i.e., Net <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">HR</sub> ). The losses obtained by LR frames and network outputs are used to optimize both Net <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LR</sub> and Net <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">HR</sub> . In the testing phase, the trained Net <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">HR</sub> is applied to generate the SR results of LR frames. In contrast to the existing video satellite SR methods, our SingleVSR does not require any assumption on degradation or any additional training data except for the single video to be tested. Experiments performed on Jilin-1 and OVS-1 satellite videos demonstrate the superiority of the proposed method.

Dose Super-Resolution in Prostate Volumetric Modulated Arc Therapy Using Cascaded Deep Learning Networks.

PurposeThis study proposes a cascaded network model for generating high-resolution doses (i.e., a 1 mm grid) from low-resolution doses (i.e., ≥3 mm grids) with reduced computation time.MethodsUsing the anisotropic analytical algorithm with three grid sizes (1, 3, and 5 mm) and the Acuros XB algorithm with two grid sizes (1 and 3 mm), dose distributions were calculated for volumetric modulated arc therapy plans for 73 prostate cancer patients. Our cascaded network model consisted of a hierarchically densely connected U-net (HD U-net) and a residual dense network (RDN), which were trained separately following a two-dimensional slice-by-slice procedure. The first network (HD U-net) predicted the downsampled high-resolution dose (generated through bicubic downsampling of the baseline high-resolution dose) using the low-resolution dose; subsequently, the second network (RDN) predicted the high-resolution dose from the output of the first network. Further, the predicted high-resolution dose was converted to its absolute value. We quantified the network performance using the spatial/dosimetric parameters (dice similarity coefficient, mean dose, maximum dose, minimum dose, homogeneity index, conformity index, and V95%, V70%, V50%, and V30%) for the low-resolution and predicted high-resolution doses relative to the baseline high-resolution dose. Gamma analysis (between the baseline dose and the low-resolution dose/predicted high-resolution dose) was performed with a 2%/2 mm criterion and 10% threshold.ResultsThe average computation time to predict a high-resolution axial dose plane was <0.02 s. The dice similarity coefficient values for the predicted doses were closer to 1 when compared to those for the low-resolution doses. Most of the dosimetric parameters for the predicted doses agreed more closely with those for the baseline than for the low-resolution doses. In most of the parameters, no significant differences (p-value of >0.05) between the baseline and predicted doses were observed. The gamma passing rates for the predicted high-resolution does were higher than those for the low-resolution doses.ConclusionThe proposed model accurately predicted high-resolution doses for the same dose calculation algorithm. Our model uses only dose data as the input without additional data, which provides advantages of convenience to user over other dose super-resolution methods.

Learning cascaded convolutional networks for blind single image super-resolution

This paper studies the blind super-resolution of real low-quality and low-resolution (LR) images. Existing convolutional network (CNN) based approaches usually learn a single image super-resolution (SISR) model for a specific downsampler (e.g., bicubic downsampling, blurring followed by downsampling). The learned model, however, is tailored to the specific downsampler and fails to super-resolve real LR images which are degraded in more sophisticated and diverse manners. Moreover, the ground-truth high-resolution (HR) of real LR images are generally unavailable. Instead of learning from unpaired real LR-HR images or a specific downsampler, this paper learns blind SR network from a realistic, parametric degradation model by considering blurring, noise, downsampling, and even JPEG compression. In contrast to direct blind reconstruction of HR image, the proposed model adopts a cascaded architecture for noise estimation, blurring estimation, and non-blind SR, which can be jointly end-to-end learned from training data and benefit generalization ability. By taking the bicubicly upscaled LR image as input to non-blind SR, the proposed method can present a single unified model for blind SR with any upscaling factors and varying degradation parameters. Experimental results show that the proposed method performs favorably on synthetic and real LR images.

A single video super-resolution GAN for multiple downsampling operators based on pseudo-inverse image formation models

The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. A large amount of current CNN-based Video Super-Resolution methods are designed and trained to handle a specific degradation operator (e.g., bicubic downsampling) and are not robust to mismatch between training and testing degradation models. This causes their performance to deteriorate in real-life applications. Furthermore, many of them use the Mean-Squared-Error as the only loss during learning, causing the resulting images to be too smooth. In this work we propose a new Convolutional Neural Network for video super resolution which is robust to multiple degradation models. During training, which is performed on a large dataset of scenes with slow and fast motions, it uses the pseudo-inverse image formation model as part of the network architecture in conjunction with perceptual losses and a smoothness constraint that eliminates the artifacts originating from these perceptual losses. The experimental validation shows that our approach outperforms current state-of-the-art methods and is robust to multiple degradations.

Learning a Convolutional Neural Network for Image Compact-Resolution.

We study the dual problem of image super-resolution (SR), which we term image compact-resolution (CR). Opposite to image SR that hallucinates a visually plausible high-resolution image given a low-resolution input, image CR provides a low-resolution version of a high-resolution image, such that the low-resolution version is both visually pleasing and as informative as possible compared to the high-resolution image. We propose a convolutional neural network (CNN) for image CR, namely, CNN-CR, inspired by the great success of CNN for image SR. Specifically, we translate the requirements of image CR into operable optimization targets for training CNN-CR: the visual quality of the compact resolved image is ensured by constraining its difference from a naively downsampled version and the information loss of image CR is measured by upsampling/super-resolving the compact-resolved image and comparing that to the original image. Accordingly, CNN-CR can be trained either separately or jointly with a CNN for image SR. We explore different training strategies as well as different network structures for CNN-CR. Our experimental results show that the proposed CNN-CR clearly outperforms simple bicubic downsampling and achieves on average 2.25 dB improvement in terms of the reconstruction quality on a large collection of natural images. We further investigate two applications of image CR, i.e., low-bit-rate image compression and image retargeting. Experimental results show that the proposed CNN-CR helps achieve significant bits saving than High Efficiency Video Coding when applied to image compression and produce visually pleasing results when applied to image retargeting.

Block effect reduction by the 1-D gray polynomial interpolation

In this paper, the one-dimensional gray polynomial interpolation (1-D GPI) developed for image enlargement in Hsieh et al. (2007) [27] is applied to reduce the block effect in the block discrete cosine transform (BDCT) image/video coders. Note that the block effect in the BDCT coders results from insufficient bits for transform coefficients. An interpolation approach is proposed to relieve the block effect problem. The proposed approach consists of three stages. First, the input image/frame is down sampled by the direct down sampling (DDS) scheme to reduce the amount of data. Second, the down sampled image/frame is put into a BDCT coder, such as the JPEG and the MPEG-2. Finally, the 1-D GPI is applied to enlarge the decoded image. When the JPEG and the MPEG-2 are used as BDCT coders, the coding systems are called the JPEG-GPI and the MPEG-GPI, respectively. The proposed JPEG-GPI and MPEG-GPI are verified through examples. Simulation results indicate that both the JPEG-GPI and the MPEG-GPI are able to effectively reduce the block effect significantly and therefore the subjective visual quality improved in the given examples. Note that (i) the down sampling scheme in the first stage can be any down sampling scheme other than the DDS, and (ii) the interpolation approach in the third stage may be different from the 1-D GPI. Thus, various down sampling schemes, the nearest neighbor down sampling (NNDS), the bilinear down sampling (BLDS), and the bicubic down sampling (BCDS) schemes are under consideration. These down sampling schemes are used to replace the DDS in the JPEG-GPI and the MPEG-GPI to investigate the effect on the coding performance. The simulation results show that the DDS always gives the highest PSNR for all cases under same condition. Moreover, the 1-GPI is substituted by popular 2-D interpolation approaches, the nearest neighbor interpolation (NNI), the bilinear interpolation (BLI), and the bicubic interpolation (BCI). With the DDS scheme, the simulation results indicate that the JPEG-BLI has a little bit better PSNR than the JPEG-GPI for all cases while similar visual quality of reconstructed image is found. When compared with the MPEG-GPI, the MPEG-BCI has higher PSNR when the DDS is employed. And the reconstructed frames from the MPEG-GPI and the MPEG-BCI have similar visual quality. In summary, by the simulation results the proposed coding system, as expected, is able to significantly reduce the block effect happened in the cases of the low bit rate coding or high compression ratio.