Recently, learned image compression methods have developed rapidly and exhibited excellent rate-distortion performance when compared to traditional standards, such as JPEG, JPEG2000 and BPG. However, the learning-based methods suffer from high computational costs, which is not beneficial for deployment on devices with limited resources. To this end, we propose shift-addition parallel modules (SAPMs), including SAPM-E for the encoder and SAPM-D for the decoder, to largely reduce the energy consumption. To be specific, they can be taken as plug-and-play components to upgrade existing CNN-based architectures, where the shift branch is used to extract large-grained features as compared to small-grained features learned by the addition branch. Furthermore, we thoroughly analyze the probability distribution of latent representations and propose to use Laplace Mixture Likelihoods for more accurate entropy estimation. Experimental results demonstrate that the proposed methods can achieve comparable or even better performance on both PSNR and MS-SSIM metrics to that of the convolutional counterpart with an about 2x energy reduction.
Region extraction is necessary in a wide range of applications, from object detection in autonomous driving to analysis of subcellular morphology in cell biology. There exist two main approaches: convex hull extraction, for which exact and efficient algorithms exist and concave hulls, which are better at capturing real-world shapes but do not have a single solution. Especially in the context of a uniform grid, concave hull algorithms are largely approximate, sacrificing region integrity for spatial and temporal efficiency. In this study, we present a novel algorithm that can provide vertex-minimized concave hulls with maximal (i.e. pixel-perfect) resolution and is tunable for speed-efficiency tradeoffs. Our method provides advantages in multiple downstream applications including data compression, retrieval, visualization, and analysis. To demonstrate the practical utility of our approach, we focus on image compression. We demonstrate significant improvements through context-dependent compression on disparate regions within a single image (entropy encoding for noisy and predictive encoding for the structured regions). We show that these improvements range from biomedical images to natural images. Beyond image compression, our algorithm can be applied more broadly to aid in a wide range of practical applications for data retrieval, visualization, and analysis.
Recently, deep learning-based image compression has made signifcant progresses, and has achieved better ratedistortion (R-D) performance than the latest traditional method, H.266/VVC, in both subjective metric and the more challenging objective metric. However, a major problem is that many leading learned schemes cannot maintain a good trade-off between performance and complexity. In this paper, we propose an effcient and effective image coding framework, which achieves similar R-D performance with lower complexity than the state of the art. First, we develop an improved multi-scale residual block (MSRB) that can expand the receptive feld and is easier to obtain global information. It can further capture and reduce the spatial correlation of the latent representations. Second, a more advanced importance map network is introduced to adaptively allocate bits to different regions of the image. Third, we apply a 2D post-quantization flter (PQF) to reduce the quantization error, motivated by the Sample Adaptive Offset (SAO) flter in video coding. Moreover, We fnd that the complexity of encoder and decoder have different effects on image compression performance. Based on this observation, we design an asymmetric paradigm, in which the encoder employs three stages of MSRBs to improve the learning capacity, whereas the decoder only needs one stage of MSRB to yield satisfactory reconstruction, thereby reducing the decoding complexity without sacrifcing performance. Experimental results show that compared to the state-of-the-art method, the encoding and decoding time of the proposed method are about 17 times faster, and the R-D performance is only reduced by less than 1% on both Kodak and Tecnick datasets, which is still better than H.266/VVC(4:4:4) and other recent learning-based methods. Our source code is publicly available at https://github.com/fengyurenpingsheng.
Learned Image Compression (LIC) gradually became more and more famous in these years. The hyperprior-module-based LIC models have achieved remarkable rate-distortion performance. However, the memory cost of these LIC models is too large to actually apply them to various devices, especially to portable or edge devices. The parameter scale is directly linked with memory cost. In our research, we found the hyperprior module is not only highly over-parameterized, but also its latent representation contains redundant information. Therefore, we propose a novel pruning method named ERHP in this paper to efficiently reduce the memory cost of hyperprior module, while improving the network performance. The experiments show our method is effective, reducing at least 22.6% parameters in the whole model while achieving better rate-distortion performance.
Recently, more and more images are compressed and sent to the back-end devices for the machine analysis tasks~(\textit{e.g.,} object detection) instead of being purely watched by humans. However, most traditional or learned image codecs are designed to minimize the distortion of the human visual system without considering the increased demand from machine vision systems. In this work, we propose a preprocessing enhanced image compression method for machine vision tasks to address this challenge. Instead of relying on the learned image codecs for end-to-end optimization, our framework is built upon the traditional non-differential codecs, which means it is standard compatible and can be easily deployed in practical applications. Specifically, we propose a neural preprocessing module before the encoder to maintain the useful semantic information for the downstream tasks and suppress the irrelevant information for bitrate saving. Furthermore, our neural preprocessing module is quantization adaptive and can be used in different compression ratios. More importantly, to jointly optimize the preprocessing module with the downstream machine vision tasks, we introduce the proxy network for the traditional non-differential codecs in the back-propagation stage. We provide extensive experiments by evaluating our compression method for two representative downstream tasks with different backbone networks. Experimental results show our method achieves a better trade-off between the coding bitrate and the performance of the downstream machine vision tasks by saving about 20% bitrate.
Recent years have witnessed the rapid development of image storage and transmission systems, in which image compression plays an important role. Generally speaking, image compression algorithms are developed to ensure good visual quality at limited bit rates. However, due to the different compression optimization methods, the compressed images may have different levels of quality, which needs to be evaluated quantificationally. Nowadays, the mainstream full-reference (FR) metrics are effective to predict the quality of compressed images at coarse-grained levels (the bit rates differences of compressed images are obvious), however, they may perform poorly for fine-grained compressed images whose bit rates differences are quite subtle. Therefore, to better improve the Quality of Experience (QoE) and provide useful guidance for compression algorithms, we propose a full-reference image quality assessment (FR-IQA) method for compressed images of fine-grained levels. Specifically, the reference images and compressed images are first converted to $YCbCr$ color space. The gradient features are extracted from regions that are sensitive to compression artifacts. Then we employ the Log-Gabor transformation to further analyze the texture difference. Finally, the obtained features are fused into a quality score. The proposed method is validated on the fine-grained compression image quality assessment (FGIQA) database, which is especially constructed for assessing the quality of compressed images with close bit rates. The experimental results show that our metric outperforms mainstream FR-IQA metrics on the FGIQA database. We also test our method on other commonly used compression IQA databases and the results show that our method obtains competitive performance on the coarse-grained compression IQA databases as well.
In privacy-preserving machine learning, it is common that the owner of the learned model does not have any physical access to the data. Instead, only a secured remote access to a data lake is granted to the model owner without any ability to retrieve data from the data lake. Yet, the model owner may want to export the trained model periodically from the remote repository and a question arises whether this may cause is a risk of data leakage. In this paper, we introduce the concept of data stealing attack during the export of neural networks. It consists in hiding some information in the exported network that allows the reconstruction outside the data lake of images initially stored in that data lake. More precisely, we show that it is possible to train a network that can perform lossy image compression and at the same time solve some utility tasks such as image segmentation. The attack then proceeds by exporting the compression decoder network together with some image codes that leads to the image reconstruction outside the data lake. We explore the feasibility of such attacks on databases of CT and MR images, showing that it is possible to obtain perceptually meaningful reconstructions of the target dataset, and that the stolen dataset can be used in turns to solve a broad range of tasks. Comprehensive experiments and analyses show that data stealing attacks should be considered as a threat for sensitive imaging data sources.
Lidars are depth measuring sensors widely used in autonomous driving and augmented reality. However, the large volume of data produced by lidars can lead to high costs in data storage and transmission. While lidar data can be represented as two interchangeable representations: 3D point clouds and range images, most previous work focus on compressing the generic 3D point clouds. In this work, we show that directly compressing the range images can leverage the lidar scanning pattern, compared to compressing the unprojected point clouds. We propose a novel data-driven range image compression algorithm, named RIDDLE (Range Image Deep DeLta Encoding). At its core is a deep model that predicts the next pixel value in a raster scanning order, based on contextual laser shots from both the current and past scans (represented as a 4D point cloud of spherical coordinates and time). The deltas between predictions and original values can then be compressed by entropy encoding. Evaluated on the Waymo Open Dataset and KITTI, our method demonstrates significant improvement in the compression rate (under the same distortion) compared to widely used point cloud and range image compression algorithms as well as recent deep methods.
The discrete Hartley transform (DHT) is a useful tool for medical image coding. The three-dimensional DHT (3D DHT) can be employed to compress medical image data, such as magnetic resonance and X-ray angiography. However, the computation of the 3D DHT involves several multiplications by irrational quantities, which require floating-point arithmetic and inherent truncation errors. In recent years, a significant progress in wireless and implantable biomedical devices has been achieved. Such devices present critical power and hardware limitations. The multiplication operation demands higher hardware, power, and time consumption than other arithmetic operations, such as addition and bit-shifts. In this work, we present a set of multiplierless DHT approximations, which can be implemented with fixed-point arithmetic. We derive 3D DHT approximations by employing tensor formalism. Such proposed methods present prominent computational savings compared to the usual 3D DHT approach, being appropriate for devices with limited resources. The proposed transforms are applied in a lossy 3D DHT-based medical image compression algorithm, presenting practically the same level of visual quality ($>98\%$ in terms of SSIM) at a considerable reduction in computational effort ($100 \%$ multiplicative complexity reduction). Furthermore, we implemented the proposed 3D transforms in an ARM Cortex-M0+ processor employing the low-cost Raspberry Pi Pico board. The execution time was reduced by $\sim$70% compared to the usual 3D DHT and $\sim$90% compared to 3D DCT.
Learned image compression (LIC) has reached a comparable coding gain with traditional hand-crafted methods such as VVC intra. However, the large network complexity prohibits the usage of LIC on resource-limited embedded systems. Network quantization is an efficient way to reduce the network burden. This paper presents a quantized LIC (QLIC) by channel splitting. First, we explore that the influence of quantization error to the reconstruction error is different for various channels. Second, we split the channels whose quantization has larger influence to the reconstruction error. After the splitting, the dynamic range of channels is reduced so that the quantization error can be reduced. Finally, we prune several channels to keep the number of overall channels as origin. By using the proposal, in the case of 8-bit quantization for weight and activation of both main and hyper path, we can reduce the BD-rate by 0.61%-4.74% compared with the previous QLIC. Besides, we can reach better coding gain compared with the state-of-the-art network quantization method when quantizing MS-SSIM models. Moreover, our proposal can be combined with other network quantization methods to further improve the coding gain. The moderate coding loss caused by the quantization validates the feasibility of the hardware implementation for QLIC in the future.
In the past years, learned image compression (LIC) has achieved remarkable performance. The recent LIC methods outperform VVC in both PSNR and MS-SSIM. However, the low bit-rate reconstructions of LIC suffer from artifacts such as blurring, color drifting and texture missing. Moreover, those varied artifacts make image quality metrics correlate badly with human perceptual quality. In this paper, we propose PO-ELIC, i.e., Perception-Oriented Efficient Learned Image Coding. To be specific, we adapt ELIC, one of the state-of-the-art LIC models, with adversarial training techniques. We apply a mixture of losses including hinge-form adversarial loss, Charbonnier loss, and style loss, to finetune the model towards better perceptual quality. Experimental results demonstrate that our method achieves comparable perceptual quality with HiFiC with much lower bitrate.
Deep learning techniques have shown promising results in image compression, with competitive bitrate and image reconstruction quality from compressed latent. However, while image compression has progressed towards a higher peak signal-to-noise ratio (PSNR) and fewer bits per pixel (bpp), their robustness to adversarial images has never received deliberation. In this work, we, for the first time, investigate the robustness of image compression systems where imperceptible perturbation of input images can precipitate a significant increase in the bitrate of their compressed latent. To characterize the robustness of state-of-the-art learned image compression, we mount white-box and black-box attacks. Our white-box attack employs fast gradient sign method on the entropy estimation of the bitstream as its bitrate approximation. We propose DCT-Net simulating JPEG compression with architectural simplicity and lightweight training as the substitute in the black-box attack and enable fast adversarial transferability. Our results on six image compression models, each with six different bitrate qualities (thirty-six models in total), show that they are surprisingly fragile, where the white-box attack achieves up to 56.326x and black-box 1.947x bpp change. To improve robustness, we propose a novel compression architecture factorAtn which incorporates attention modules and a basic factorized entropy model, resulting in a promising trade-off between the rate-distortion performance and robustness to adversarial attacks that surpasses existing learned image compressors.
Cardiomegaly is indeed a medical disease in which the heart is enlarged. Cardiomegaly is better to handle if caught early, so early detection is critical. The chest X-ray, being one of the most often used radiography examinations, has been used to detect and visualize abnormalities of human organs for decades. X-ray is also a significant medical diagnosis tool for cardiomegaly. Even for domain experts, distinguishing the many types of diseases from the X-ray is a difficult and time-consuming task. Deep learning models are also most effective when used on huge data sets, yet due to privacy concerns, large datasets are rarely available inside the medical industry. A Deep learning-based customized retrained U-Net model for detecting Cardiomegaly disease is presented in this research. In the training phase, chest X-ray images from the "ChestX-ray8" open source real dataset are used. To reduce computing time, this model performs data preprocessing, picture improvement, image compression, and classification before moving on to the training step. The work used a chest x-ray image dataset to simulate and produced a diagnostic accuracy of 94%, a sensitivity of 96.2 percent, and a specificity of 92.5 percent, which beats prior pre-trained model findings for identifying Cardiomegaly disease.
This paper describes a CNN-based multi-frame post-processing approach based on a perceptually-inspired Generative Adversarial Network architecture, CVEGAN. This method has been integrated with the Versatile Video Coding Test Model (VTM) 15.2 to enhance the visual quality of the final reconstructed content. The evaluation results on the CLIC 2022 validation sequences show consistent coding gains over the original VVC VTM at the same bitrates when assessed by PSNR. The integrated codec has been submitted to the Challenge on Learned Image Compression (CLIC) 2022 (video track), and the team name associated with this submission is BVI_VC.
Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression can cause severe decline in performance of deep Convolution Neural Network (CNN) architectures even when mild compression is applied and the resulting compressed imagery is visually identical. In this work, we apply the lossy JPEG compression method with six discrete levels of increasing compression {95, 75, 50, 15, 10, 5} to infrared band (thermal) imagery. Our study quantitatively evaluates the affect that increasing levels of lossy compression has upon the performance of characteristically diverse object detection architectures (Cascade-RCNN, FSAF and Deformable DETR) with respect to varying sizes of objects present in the dataset. When training and evaluating on uncompressed data as a baseline, we achieve maximal mean Average Precision (mAP) of 0.823 with Cascade R-CNN across the FLIR dataset, outperforming prior work. The impact of the lossy compression is more extreme at higher compression levels (15, 10, 5) across all three CNN architectures. However, re-training models on lossy compressed imagery notably ameliorated performances for all three CNN models with an average increment of ~76% (at higher compression level 5). Additionally, we demonstrate the relative sensitivity of differing object areas {tiny, small, medium, large} with respect to the compression level. We show that tiny and small objects are more sensitive to compression than medium and large objects. Overall, Cascade R-CNN attains the maximal mAP across most of the object area categories.
Image denoising is an important low-level computer vision task, which aims to reconstruct a noise-free and high-quality image from a noisy image. With the development of deep learning, convolutional neural network (CNN) has been gradually applied and achieved great success in image denoising, image compression, image enhancement, etc. Recently, Transformer has been a hot technique, which is widely used to tackle computer vision tasks. However, few Transformer-based methods have been proposed for low-level vision tasks. In this paper, we proposed an image denoising network structure based on Transformer, which is named DenSformer. DenSformer consists of three modules, including a preprocessing module, a local-global feature extraction module, and a reconstruction module. Specifically, the local-global feature extraction module consists of several Sformer groups, each of which has several ETransformer layers and a convolution layer, together with a residual connection. These Sformer groups are densely skip-connected to fuse the feature of different layers, and they jointly capture the local and global information from the given noisy images. We conduct our model on comprehensive experiments. Experimental results prove that our DenSformer achieves improvement compared to some state-of-the-art methods, both for the synthetic noise data and real noise data, in the objective and subjective evaluations.
Video and image coding for machines (VCM) is an emerging field that aims to develop compression methods resulting in optimal bitstreams when the decoded frames are analyzed by a neural network. Several approaches already exist improving classic hybrid codecs for this task. However, neural compression networks (NCNs) have made an enormous progress in coding images over the last years. Thus, it is reasonable to consider such NCNs, when the information sink at the decoder side is a neural network as well. Therefore, we build-up an evaluation framework analyzing the performance of four state-of-the-art NCNs, when a Mask R-CNN is segmenting objects from the decoded image. The compression performance is measured by the weighted average precision for the Cityscapes dataset. Based on that analysis, we find that networks with leaky ReLU as non-linearity and training with SSIM as distortion criteria results in the highest coding gains for the VCM task. Furthermore, it is shown that the GAN-based NCN architecture achieves the best coding performance and even out-performs the recently standardized Versatile Video Coding (VVC) for the given scenario.
Nowadays, hyperspectral imaging is recognized as cornerstone remote sensing technology. The explosive growth in image data volume and instrument data rates, compete with limited on-board storage resources and downlink bandwidth, making hyperspectral image data compression a mission critical on-board processing task. The Consultative Committee for Space Data Systems (CCSDS) extended the previous issue of the CCSDS-123.0 Recommended Standard for multi- and hyperspectral image compression to provide with Near-Lossless compression functionality. A key feature of the CCSDS-123.0-B-2 is the improved Hybrid Entropy Coder, which at low bit rates, provides substantially better compression performance than the Issue 1 entropy coders. In this paper, we introduce a high-throughput hardware implementation of the CCSDS-123.0-B-2 Hybrid Entropy Coder. The introduced architecture exploits the systolic design pattern to provide modularity and latency insensitivity in a deep and elastic pipeline achieving a constant throughput of 1 sample/cycle with a small FPGA resource footprint. This architecture is described in portable VHDL RTL and is implemented, validated and demonstrated on a commercially available Xilinx KCU105 development board hosting a Xilinx Kintex Ultrascale XCKU040 SRAM FPGA, and thus, is directly transferable to Xilinx Radiation Tolerant Kintex UltraScale XQRKU060 space-grade devices for space deployments. Moreover, state-of-the-art SpaceFibre (ECSS-E-ST-50-11C) serial link interface and test equipment were used in the validation platform to emulate an on-board deployment. The introduced CCSDS-123.0-B-2 Hybrid Entropy Encoder achieves a constant throughput performance of 305 MSamples/s. To the best of our knowledge, this is the first published fully-compliant architecture and high-throughput implementation of the CCSDS-123.0-B-2 Hybrid Entropy Coder, targeting space-grade FPGA technology.
We consider the image and video compression on resource limited platforms. An ultra low-cost image encoder, named Block Modulating Video Compression (BMVC) with an encoding complexity ${\cal O}(1)$ is proposed to be implemented on mobile platforms with low consumption of power and computation resources. We also develop two types of BMVC decoders, implemented by deep neural networks. The first BMVC decoder is based on the Plug-and-Play (PnP) algorithm, which is flexible to different compression ratios. And the second decoder is a memory efficient end-to-end convolutional neural network, which aims for real-time decoding. Extensive results on the high definition images and videos demonstrate the superior performance of the proposed codec and the robustness against bit quantization.
Image compression has raised widespread interest recently due to its significant importance for multimedia storage and transmission. Meanwhile, a reliable image quality assessment (IQA) for compressed images can not only help to verify the performance of various compression algorithms but also help to guide the compression optimization in turn. In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space. It is known that the compression artifacts are usually non-uniformly distributed with diverse distortion types and degrees. To warp the compressed images into the shared representation space while maintaining the complex distortion information, we extract the hierarchical feature representations from each stage of the Swin Transformer. Besides, we utilize cross attention operation to map the extracted feature representations into a learned Swin distance space. Experimental results show that the proposed metric achieves higher consistency with human's perceptual judgment compared with both traditional methods and learning-based methods on CLIC datasets.