Xiaolin Wu

Yuanchao Bai, Xianming Liu, Kai Wang et al.

Lossless and near-lossless image compression is of paramount importance to professional users in many technical fields, such as medicine, remote sensing, precision engineering and scientific research. But despite rapidly growing research interests in learning-based image compression, no published method offers both lossless and near-lossless modes. In this paper, we propose a unified and powerful deep lossy plus residual (DLPR) coding framework for both lossless and near-lossless image compression. In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals. We solve the joint lossy and residual compression problem in the approach of VAEs, and add autoregressive context modeling of the residuals to enhance lossless compression performance. In the near-lossless mode, we quantize the original residuals to satisfy a given $\ell_\infty$ error bound, and propose a scalable near-lossless compression scheme that works for variable $\ell_\infty$ bounds instead of training multiple networks. To expedite the DLPR coding, we increase the degree of algorithm parallelization by a novel design of coding context, and accelerate the entropy coding with adaptive residual interval. Experimental results demonstrate that the DLPR coding system achieves both the state-of-the-art lossless and near-lossless image compression performance with competitive coding speed.

Xi Zhang, Xiaolin Wu

Recently, numerous end-to-end optimized image compression neural networks have been developed and proved themselves as leaders in rate-distortion performance. The main strength of these learnt compression methods is in powerful nonlinear analysis and synthesis transforms that can be facilitated by deep neural networks. However, out of operational expediency, most of these end-to-end methods adopt uniform scalar quantizers rather than vector quantizers, which are information-theoretically optimal. In this paper, we present a novel Lattice Vector Quantization scheme coupled with a spatially Adaptive Companding (LVQAC) mapping. LVQ can better exploit the inter-feature dependencies than scalar uniform quantization while being computationally almost as simple as the latter. Moreover, to improve the adaptability of LVQ to source statistics, we couple a spatially adaptive companding (AC) mapping with LVQ. The resulting LVQAC design can be easily embedded into any end-to-end optimized image compression system. Extensive experiments demonstrate that for any end-to-end CNN image compression models, replacing uniform quantizer by LVQAC achieves better rate-distortion performance without significantly increasing the model complexity.

Yanhui Guo, Fangzhou Luo, Xiaolin Wu

Image signal processing (ISP) pipeline plays a fundamental role in digital cameras, which converts raw Bayer sensor data to RGB images. However, ISP-generated images usually suffer from imperfections due to the compounded degradations that stem from sensor noises, demosaicing noises, compression artifacts, and possibly adverse effects of erroneous ISP hyperparameter settings such as ISO and gamma values. In a general sense, these ISP imperfections can be considered as degradations. The highly complex mechanisms of ISP degradations, some of which are even unknown, pose great challenges to the generalization capability of deep neural networks (DNN) for image restoration and to their adaptability to downstream tasks. To tackle the issues, we propose a novel DNN approach to learn degradation-independent representations (DiR) through the refinement of a self-supervised learned baseline representation. The proposed DiR learning technique has remarkable domain generalization capability and consequently, it outperforms state-of-the-art methods across various downstream tasks, including blind image restoration, object detection, and instance segmentation, as verified in our experiments.

Hao Xu, Xi Zhang, Xiaolin Wu

Compressing a set of unordered points is far more challenging than compressing images/videos of regular sample grids, because of the difficulties in characterizing neighboring relations in an irregular layout of points. Many researchers resort to voxelization to introduce regularity, but this approach suffers from quantization loss. In this research, we use the KNN method to determine the neighborhoods of raw surface points. This gives us a means to determine the spatial context in which the latent features of 3D points are compressed by arithmetic coding. As such, the conditional probability model is adaptive to local geometry, leading to significant rate reduction. Additionally, we propose a dual-layer architecture where a non-learning base layer reconstructs the main structures of the point cloud at low complexity, while a learned refinement layer focuses on preserving fine details. This design leads to reductions in model complexity and coding latency by two orders of magnitude compared to SOTA methods. Moreover, we incorporate an implicit neural representation (INR) into the refinement layer, allowing the decoder to sample points on the underlying surface at arbitrary densities. This work is the first to effectively exploit content-aware local contexts for compressing irregular raw point clouds, achieving high rate-distortion performance, low complexity, and the ability to function as an arbitrary-scale upsampling network simultaneously.

Xi Zhang, Xiaolin Wu

Ultra high resolution (UHR) images are almost always downsampled to fit small displays of mobile end devices and upsampled to its original resolution when exhibited on very high-resolution displays. This observation motivates us on jointly optimizing operation pairs of downsampling and upsampling that are spatially adaptive to image contents for maximal rate-distortion performance. In this paper, we propose an adaptive downsampled dual-layer (ADDL) image compression system. In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and compressed to form a coded base layer. For decompression the base layer is decoded and upconverted to the original resolution using a deep upsampling neural network, aided by the prior knowledge of the learned adaptive downsampling kernels. We restrict the downsampling kernels to the form of Gabor filters in order to reduce the complexity of filter optimization and also reduce the amount of side information needed by the decoder for adaptive upsampling. Extensive experiments demonstrate that the proposed ADDL compression approach of jointly optimized, spatially adaptive downsampling and upconversion outperforms the state of the art image compression methods.

Xi Zhang, Xiaolin Wu, Jiamang Wang et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities but typically require extensive computational resources and memory for inference. Post-training quantization (PTQ) can effectively reduce these demands by storing weights in lower bit-width formats. However, standard uniform quantization often leads to notable performance degradation, particularly in low-bit scenarios. In this work, we introduce a Grouped Lattice Vector Quantization (GLVQ) framework that assigns each group of weights a customized lattice codebook, defined by a learnable generation matrix. To address the non-differentiability of the quantization process, we adopt Babai rounding to approximate nearest-lattice-point search during training, which enables stable optimization of the generation matrices. Once trained, decoding reduces to a simple matrix-vector multiplication, yielding an efficient and practical quantization pipeline. Experiments on multiple benchmarks show that our approach achieves a better trade-off between model size and accuracy compared to existing post-training quantization baselines, highlighting its effectiveness in deploying large models under stringent resource constraints. Our source code is available on GitHub repository: https://github.com/xzhang9308/GLVQ.

Xi Zhang, Xiaolin Wu

It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high complexity of the latter. Lattice vector quantization (LVQ), on the other hand, presents a compelling alternative, which can exploit inter-feature dependencies more effectively while keeping computational efficiency almost the same as scalar quantization. However, traditional LVQ structures are designed/optimized for uniform source distributions, hence nonadaptive and suboptimal for real source distributions of latent code space for Neural image compression tasks. In this paper, we propose a novel learning method to overcome this weakness by designing the rate-distortion optimal lattice vector quantization (OLVQ) codebooks with respect to the sample statistics of the latent features to be compressed. By being able to better fit the LVQ structures to any given latent sample distribution, the proposed OLVQ method improves the rate-distortion performances of the existing quantization schemes in neural image compression significantly, while retaining the amenability of uniform scalar quantization.

Hao Xu, Xiaolin Wu, Xi Zhang

3D Gaussian Splatting (3DGS) is rapidly gaining popularity for its photorealistic rendering quality and real-time performance, but it generates massive amounts of data. Hence compressing 3DGS data is necessary for the cost effectiveness of 3DGS models. Recently, several anchor-based neural compression methods have been proposed, achieving good 3DGS compression performance. However, they all rely on uniform scalar quantization (USQ) due to its simplicity. A tantalizing question is whether more sophisticated quantizers can improve the current 3DGS compression methods with very little extra overhead and minimal change to the system. The answer is yes by replacing USQ with lattice vector quantization (LVQ). To better capture scene-specific characteristics, we optimize the lattice basis for each scene, improving LVQ's adaptability and R-D efficiency. This scene-adaptive LVQ (SALVQ) strikes a balance between the R-D efficiency of vector quantization and the low complexity of USQ. SALVQ can be seamlessly integrated into existing 3DGS compression architectures, enhancing their R-D performance with minimal modifications and computational overhead. Moreover, by scaling the lattice basis vectors, SALVQ can dynamically adjust lattice density, enabling a single model to accommodate multiple bit rate targets. This flexibility eliminates the need to train separate models for different compression levels, significantly reducing training time and memory consumption.

Hao Wang, Xiaolin Wu, Xi Zhang et al.

Nighttime photography is severely degraded by light pollution induced by pervasive artificial lighting in urban environments. After long-range scattering and spatial diffusion, unwanted artificial light overwhelms natural night luminance, generates skyglow that washes out the view of stars and celestial objects and produces halos and glow artifacts around light sources. Unlike nighttime dehazing, which aims to improve detail legibility through thick air, the objective of light pollution removal is to restore the pristine night appearance by neutralizing the radiative footprint of ground lighting. In this paper we introduce a physically-based degradation model that adds to the previous ones for nighttime dehazing two critical aspects; (i) anisotropic spread of directional light sources, and (ii) skyglow caused by invisible surface lights behind skylines. In addition, we construct a training strategy that leverages large generative model and synthetic-real coupling to compensate for the scarcity of paired real data and enhance generalization. Extensive experiments demonstrate that the proposed formulation and learning framework substantially reduce light pollution artifacts and better recover authentic night imagery than prior nighttime restoration methods.

Xi Zhang, Xiaolin Wu

Recently, several look-up table (LUT) methods were developed to greatly expedite the inference of CNNs in a classical strategy of trading space for speed. However, these LUT methods suffer from a common drawback of limited receptive field of the convolution kernels due to the combinatorial explosion of table size. This research aims to expand the CNN receptive field with a fixed table size, thereby enhancing the performance of LUT-driven fast CNN inference while maintaining the same space complexity. To achieve this goal, various techniques are proposed. The main contribution is a novel approach of learning an optimal lattice vector quantizer that adaptively allocates the quantization resolution across data dimensions based on their significance to the inference task. In addition, the lattice vector quantizer offers an inherently more accurate approximation of CNN kernels than scalar quantizer as used in current practice. Furthermore, we introduce other receptive field expansion strategies, including irregular dilated convolutions and a U-shaped cascaded LUT structure, designed to capture multi-level contextual information without inflating table size. Together, these innovations allow our approach to effectively balance speed, accuracy, and memory efficiency, demonstrating significant improvements over existing LUT methods.

Hao Xu, Xiaolin Wu, Xi Zhang

3D Gaussian Splatting (3DGS) has gained popularity for its fast and high-quality rendering, but it has a very large memory footprint incurring high transmission and storage overhead. Recently, some neural compression methods, such as Scaffold-GS, were proposed for 3DGS but they did not adopt the approach of end-to-end optimized analysis-synthesis transforms which has been proven highly effective in neural signal compression. Without an appropriate analysis transform, signal correlations cannot be removed by sparse representation. Without such transforms the only way to remove signal redundancies is through entropy coding driven by a complex and expensive context modeling, which results in slower speed and suboptimal rate-distortion (R-D) performance. To overcome this weakness, we propose Sparsity-guided Hierarchical Transform Coding (SHTC), the first end-to-end optimized transform coding framework for 3DGS compression. SHTC jointly optimizes the 3DGS, transforms and a lightweight context model. This joint optimization enables the transform to produce representations that approach the best R-D performance possible. The SHTC framework consists of a base layer using KLT for data decorrelation, and a sparsity-coded enhancement layer that compresses the KLT residuals to refine the representation. The enhancement encoder learns a linear transform to project high-dimensional inputs into a low-dimensional space, while the decoder unfolds the Iterative Shrinkage-Thresholding Algorithm (ISTA) to reconstruct the residuals. All components are designed to be interpretable, allowing the incorporation of signal priors and fewer parameters than black-box transforms. This novel design significantly improves R-D performance with minimal additional parameters and computational overhead.

Xi Zhang, Xiaolin Wu

Table look-up realization of image restoration CNNs has the potential of achieving competitive image quality while being much faster and resource frugal than the straightforward CNN implementation. The main technical challenge facing the LUT-based CNN algorithm designers is to manage the table size without overly restricting the receptive field. The prevailing strategy is to reuse the table for small pixel patches of different orientations (apparently assuming a degree of isotropy) and then fuse the look-up results. The fusion is currently done by average pooling, which we find being ill suited to anisotropic signal structures. To alleviate the problem, we investigate and discuss anisotropic pooling methods to replace naive averaging for improving the performance of the current LUT-realizable CNN restoration methods. First, we introduce the method of generalized median pooling which leads to measurable gains over average pooling. We then extend this idea by learning data-dependent pooling coefficients for each orientation, so that they can adaptively weigh the contributions of differently oriented pixel patches. Experimental results on various restoration benchmarks show that our anisotropic pooling strategy yields both perceptually and numerically superior results compared to existing LUT-realizable CNN methods.

Zhicheng Lin, Xiaolin Wu, Xi Zhang

Deep models often suffer significant performance degradation under distribution shifts. Domain generalization (DG) seeks to mitigate this challenge by enabling models to generalize to unseen domains. Most prior approaches rely on multi-domain training or computationally intensive test-time adaptation. In contrast, we propose a complementary strategy: lightweight test-time augmentation. Specifically, we develop a novel Class-Invariant Test-Time Augmentation (CI-TTA) technique. The idea is to generate multiple variants of each input image through elastic and grid deformations that nevertheless belong to the same class as the original input. Their predictions are aggregated through a confidence-guided filtering scheme that remove unreliable outputs, ensuring the final decision relies on consistent and trustworthy cues. Extensive Experiments on PACS and Office-Home datasets demonstrate consistent gains across different DG algorithms and backbones, highlighting the effectiveness and generality of our approach.

Pei An, Jiaqi Yang, Muyao Peng et al.

Image-to-point-cloud (I2P) registration is a fundamental problem in computer vision, focusing on establishing 2D-3D correspondences between an image and a point cloud. The differential perspective-n-point (PnP) has been widely used to supervise I2P registration networks by enforcing the projective constraints on 2D-3D correspondences. However, differential PnP is highly sensitive to noise and outliers in the predicted correspondences. This issue hinders the effectiveness of correspondence learning. Inspired by the robustness of blind PnP against noise and outliers in correspondences, we propose an approximated blind PnP based correspondence learning approach. To mitigate the high computational cost of blind PnP, we simplify blind PnP to an amenable task of minimizing Chamfer distance between learned 2D and 3D keypoints, called MinCD-PnP. To effectively solve MinCD-PnP, we design a lightweight multi-task learning module, named as MinCD-Net, which can be easily integrated into the existing I2P registration architectures. Extensive experiments on 7-Scenes, RGBD-V2, ScanNet, and self-collected datasets demonstrate that MinCD-Net outperforms state-of-the-art methods and achieves a higher inlier ratio (IR) and registration recall (RR) in both cross-scene and cross-dataset settings.

Xi Zhang, Xiaolin Wu

Recently, DNN models for lossless image coding have surpassed their traditional counterparts in compression performance, reducing the previous lossless bit rate by about ten percent for natural color images. But even with these advances, mathematically lossless image compression (MLLIC) ratios for natural images still fall short of the bandwidth and cost-effectiveness requirements of most practical imaging and vision systems at present and beyond. To overcome the performance barrier of MLLIC, we question the very necessity of MLLIC. Considering that all digital imaging sensors suffer from acquisition noises, why should we insist on mathematically lossless coding, i.e., wasting bits to preserve noises? Instead, we propose a new paradigm of joint denoising and compression called functionally lossless image compression (FLLIC), which performs lossless compression of optimally denoised images (the optimality may be task-specific). Although not literally lossless with respect to the noisy input, FLLIC aims to achieve the best possible reconstruction of the latent noise-free original image. Extensive experiments show that FLLIC achieves state-of-the-art performance in joint denoising and compression of noisy images and does so at a lower computational cost.

Fangzhou Luo, Xiaolin Wu, Yanhui Guo

Almost every single image restoration problem has a closely related parameter, such as the scale factor in super-resolution, the noise level in image denoising, and the quality factor in JPEG deblocking. Although recent studies on image restoration problems have achieved great success due to the development of deep neural networks, they handle the parameter involved in an unsophisticated way. Most previous researchers either treat problems with different parameter levels as independent tasks, and train a specific model for each parameter level; or simply ignore the parameter, and train a single model for all parameter levels. The two popular approaches have their own shortcomings. The former is inefficient in computing and the latter is ineffective in performance. In this work, we propose a novel system called functional neural network (FuncNet) to solve a parametric image restoration problem with a single model. Unlike a plain neural network, the smallest conceptual element of our FuncNet is no longer a floating-point variable, but a function of the parameter of the problem. This feature makes it both efficient and effective for a parametric problem. We apply FuncNet to super-resolution, image denoising, and JPEG deblocking. The experimental results show the superiority of our FuncNet on all three parametric image restoration tasks over the state of the arts.

Yanhui Guo, Xiaolin Wu, Xiao Shu

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$\sim$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$\sim$HR image pairs using real cameras. The images are displayed on an ultra-high quality screen and captured at different resolutions. The resulting LR$\sim$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$\sim$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.

Xi Zhang, Xiaolin Wu

Arguably the most common and salient object in daily video communications is the talking head, as encountered in social media, virtual classrooms, teleconferences, news broadcasting, talk shows, etc. When communication bandwidth is limited by network congestions or cost effectiveness, compression artifacts in talking head videos are inevitable. The resulting video quality degradation is highly visible and objectionable due to high acuity of human visual system to faces. To solve this problem, we develop a multi-modality deep convolutional neural network method for restoring face videos that are aggressively compressed. The main innovation is a new DCNN architecture that incorporates known priors of multiple modalities: the video-synchronized speech signal and semantic elements of the compression code stream, including motion vectors, code partition map and quantization parameters. These priors strongly correlate with the latent video and hence they are able to enhance the capability of deep learning to remove compression artifacts. Ample empirical evidences are presented to validate the superior performance of the proposed DCNN method on face videos over the existing state-of-the-art methods.

Chang Liu, Xiaolin Wu

Nighttime photographers are often troubled by light pollution of unwanted artificial lights. Artificial lights, after scattered by aerosols in the atmosphere, can inundate the starlight and degrade the quality of nighttime images, by reducing contrast and dynamic range and causing hazes. In this paper we develop a physically-based light pollution reduction (LPR) algorithm that can substantially alleviate the aforementioned degradations of perceptual quality and restore the pristine state of night sky. The key to the success of the proposed LPR algorithm is an inverse method to estimate the spatial radiance distribution and spectral signature of ground artificial lights. Extensive experiments are carried out to evaluate the efficacy and limitations of the LPR algorithm.

Xi Zhang, Xiaolin Wu

We propose a deep learning system for attention-guided dual-layer image compression (AGDL). In the AGDL compression system, an image is encoded into two layers, a base layer and an attention-guided refinement layer. Unlike the existing ROI image compression methods that spend an extra bit budget equally on all pixels in ROI, AGDL employs a CNN module to predict those pixels on and near a saliency sketch within ROI that are critical to perceptual quality. Only the critical pixels are further sampled by compressive sensing (CS) to form a very compact refinement layer. Another novel CNN method is developed to jointly decode the two compression layers for a much refined reconstruction, while strictly satisfying the transmitted CS constraints on perceptually critical pixels. Extensive experiments demonstrate that the proposed AGDL system advances the state of the art in perception-aware image compression.

Xi Zhang, Xiaolin Wu

Recently, a provocative claim was published that number sense spontaneously emerges in a deep neural network trained merely for visual object recognition. This has, if true, far reaching significance to the fields of machine learning and cognitive science alike. In this paper, we prove the above claim to be unfortunately incorrect. The statistical analysis to support the claim is flawed in that the sample set used to identify number-aware neurons is too small, compared to the huge number of neurons in the object recognition network. By this flawed analysis one could mistakenly identify number-sensing neurons in any randomly initialized deep neural networks that are not trained at all. With the above critique we ask the question what if a deep convolutional neural network is carefully trained for numerosity? Our findings are mixed. Even after being trained with number-depicting images, the deep learning approach still has difficulties to acquire the abstract concept of numbers, a cognitive task that preschoolers perform with ease. But on the other hand, we do find some encouraging evidences suggesting that deep neural networks are more robust to distribution shift for small numbers than for large numbers.

Yanhui Guo, Xi Zhang, Xiaolin Wu

We propose a novel deep multi-modality neural network for restoring very low bit rate videos of talking heads. Such video contents are very common in social media, teleconferencing, distance education, tele-medicine, etc., and often need to be transmitted with limited bandwidth. The proposed CNN method exploits the correlations among three modalities, video, audio and emotion state of the speaker, to remove the video compression artifacts caused by spatial down sampling and quantization. The deep learning approach turns out to be ideally suited for the video restoration task, as the complex non-linear cross-modality correlations are very difficult to model analytically and explicitly. The new method is a video post processor that can significantly boost the perceptual quality of aggressively compressed talking head videos, while being fully compatible with all existing video compression standards.

Qiang Li, Xianming Liu, Kaige Han et al.

Whole slide imaging (WSI) is an emerging technology for digital pathology. The process of autofocusing is the main influence of the performance of WSI. Traditional autofocusing methods either are time-consuming due to repetitive mechanical motions, or require additional hardware and thus are not compatible to current WSI systems. In this paper, we propose the concept of \textit{virtual autofocusing}, which does not rely on mechanical adjustment to conduct refocusing but instead recovers in-focus images in an offline learning-based manner. With the initial focal position, we only perform two-shot imaging, in contrast traditional methods commonly need to conduct as many as 21 times image shooting in each tile scanning. Considering that the two captured out-of-focus images retain pieces of partial information about the underlying in-focus image, we propose a U-Net-inspired deep neural network based approach for fusing them into a recovered in-focus image. The proposed scheme is fast in tissue slides scanning, enabling a high-throughput generation of digital pathology images. Experimental results demonstrate that our scheme achieves satisfactory refocusing performance.

Xi Zhang, Xiaolin Wu

In many professional fields, such as medicine, remote sensing and sciences, users often demand image compression methods to be mathematically lossless. But lossless image coding has a rather low compression ratio (around 2:1 for natural images). The only known technique to achieve significant compression while meeting the stringent fidelity requirements is the methodology of $\ell_\infty$-constrained coding that was developed and standardized in nineties. We make a major progress in $\ell_\infty$-constrained image coding after two decades, by developing a novel CNN-based soft $\ell_\infty$-constrained decoding method. The new method repairs compression defects by using a restoration CNN called the $\ell_\infty\mbox{-SDNet}$ to map a conventionally decoded image to the latent image. A unique strength of the $\ell_\infty\mbox{-SDNet}$ is its ability to enforce a tight error bound on a per pixel basis. As such, no small distinctive structures of the original image can be dropped or distorted, even if they are statistical outliers that are otherwise sacrificed by mainstream CNN restoration methods. More importantly, this research ushers in a new image compression system of $\ell_\infty$-constrained encoding and deep soft decoding ($\ell_\infty\mbox{-ED}^2$). The $\ell_\infty \mbox{-ED}^2$ approach beats the best of existing lossy image compression methods (e.g., BPG, WebP, etc.) not only in $\ell_\infty$ but also in $\ell_2$ error metric and perceptual quality, for bit rates near the threshold of perceptually transparent reconstruction. Operationally, the new compression system is practical, with a low-complexity real-time encoder and a cascade decoder consisting of a fast initial decoder and an optional CNN soft decoder.

Seyed Mehdi Ayyoubzadeh, Xiaolin Wu

We present a CNN-based predictive lossless compression scheme for raw color mosaic images of digital cameras. This specialized application problem was previously understudied but it is now becoming increasingly important, because modern CNN methods for image restoration tasks (e.g., superresolution, low lighting enhancement, deblurring), must operate on original raw mosaic images to obtain the best possible results. The key innovation of this paper is a high-order nonlinear CNN predictor of spatial-spectral mosaic patterns. The deep learning prediction can model highly complex sample dependencies in spatial-spectral mosaic images more accurately and hence remove statistical redundancies more thoroughly than existing image predictors. Experiments show that the proposed CNN predictor achieves unprecedented lossless compression performance on camera raw images.

Seyed Mehdi Ayyoubzadeh, Xiaolin Wu

Single Image Super-Resolution (SISR) task refers to learn a mapping from low-resolution images to the corresponding high-resolution ones. This task is known to be extremely difficult since it is an ill-posed problem. Recently, Convolutional Neural Networks (CNNs) have achieved state of the art performance on SISR. However, the images produced by CNNs do not contain fine details of the images. Generative Adversarial Networks (GANs) aim to solve this issue and recover sharp details. Nevertheless, GANs are notoriously difficult to train. Besides that, they generate artifacts in the high-resolution images. In this paper, we have proposed a method in which CNNs try to align images in different spaces rather than only the pixel space. Such a space is designed using convex optimization techniques. CNNs are encouraged to learn high-frequency components of the images as well as low-frequency components. We have shown that the proposed method can recover fine details of the images and it is stable in the training process.

Xi Zhang, Xiaolin Wu, Jun Du

Given the success of the deep convolutional neural networks (DCNNs) in applications of visual recognition and classification, it would be tantalizing to test if DCNNs can also learn spatial concepts, such as straightness, convexity, left/right, front/back, relative size, aspect ratio, polygons, etc., from varied visual examples of these concepts that are simple and yet vital for spatial reasoning. Much to our dismay, extensive experiments of the type of cognitive psychology demonstrate that the data-driven deep learning (DL) cannot see through superficial variations in visual representations and grasp the spatial concept in abstraction. The root cause of failure turns out to be the learning methodology, not the computational model of the neural network itself. By incorporating task-specific convolutional kernels, we are able to construct DCNNs for spatial cognition tasks that can generalize to input images not drawn from the same distribution of the training set. This work raises a precaution that without manually-incorporated priors or features DCCNs may fail spatial cognitive tasks at rudimentary level.

Seyed Mehdi Ayyoubzadeh, Xiaolin Wu

Regularization techniques are widely used to improve the generality, robustness, and efficiency of deep convolutional neural networks (DCNNs). In this paper, we propose a novel approach of regulating DCNN convolutional kernels by a structured filter bank. Comparing with the existing regularization methods, such as $\ell_1$ or $\ell_2$ minimization of DCNN kernel weights and the kernel orthogonality, which ignore sample correlations within a kernel, the use of filter bank in regularization of DCNNs can mold the DCNN kernels to common spatial structures and features (e.g., edges or textures of various orientations and frequencies) of natural images. On the other hand, unlike directly making DCNN kernels fixed filters, the filter bank regularization still allows the freedom of optimizing DCNN weights via deep learning. This new DCNN design strategy aims to combine the best of two worlds: the inclusion of structural image priors of traditional filter banks to improve the robustness and generality of DCNN solutions and the capability of modern deep learning to model complex non-linear functions hidden in training data. Experimental results on object recognition tasks show that the proposed regularization approach guides DCNNs to faster convergence and better generalization than existing regularization methods of weight decay and kernel orthogonality.

Bolin Liu, Xiao Shu, Xiaolin Wu

In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one is forced to use synthesized paired data to train the deep convolutional neural network (DCNN). However, due to the unavoidable generalization error in statistical learning, the synthetically trained DCNN often performs poorly on real world data. To overcome this problem, we propose a new general training method that can compensate for, to a large extent, the generalization errors of synthetically trained DCNNs.

Xi Zhang, Xiaolin Wu

Deep convolutional neural networks (DCNN) have enjoyed great successes in many signal processing applications because they can learn complex, non-linear causal relationships from input to output. In this light, DCNNs are well suited for the task of sequential prediction of multidimensional signals, such as images, and have the potential of improving the performance of traditional linear predictors. In this research we investigate how far DCNNs can push the envelop in terms of prediction precision. We propose, in a case study, a two-stage deep regression DCNN framework for nonlinear prediction of two-dimensional image signals. In the first-stage regression, the proposed deep prediction network (PredNet) takes the causal context as input and emits a prediction of the present pixel. Three PredNets are trained with the regression objectives of minimizing $\ell_1$, $\ell_2$ and $\ell_\infty$ norms of prediction residuals, respectively. The second-stage regression combines the outputs of the three PredNets to generate an even more precise and robust prediction. The proposed deep regression model is applied to lossless predictive image coding, and it outperforms the state-of-the-art linear predictors by appreciable margin.

Bolin Liu, Xiao Shu, Xiaolin Wu

Taking photos of optoelectronic displays is a direct and spontaneous way of transferring data and keeping records, which is widely practiced. However, due to the analog signal interference between the pixel grids of the display screen and camera sensor array, objectionable moiré (alias) patterns appear in captured screen images. As the moiré patterns are structured and highly variant, they are difficult to be completely removed without affecting the underneath latent image. In this paper, we propose an approach of deep convolutional neural network for demoiréing screen photos. The proposed DCNN consists of a coarse-scale network and a fine-scale network. In the coarse-scale network, the input image is first downsampled and then processed by stacked residual blocks to remove the moiré artifacts. After that, the fine-scale network upsamples the demoiréd low-resolution image back to the original resolution. Extensive experimental results have demonstrated that the proposed technique can efficiently remove the moiré patterns for camera acquired screen images; the new technique outperforms the existing ones.

Chang Liu, Xiaolin Wu, Xiao Shu

All existing image enhancement methods, such as HDR tone mapping, cannot recover A/D quantization losses due to insufficient or excessive lighting, (underflow and overflow problems). The loss of image details due to A/D quantization is complete and it cannot be recovered by traditional image processing methods, but the modern data-driven machine learning approach offers a much needed cure to the problem. In this work we propose a novel approach to restore and enhance images acquired in low and uneven lighting. First, the ill illumination is algorithmically compensated by emulating the effects of artificial supplementary lighting. Then a DCNN trained using only synthetic data recovers the missing detail caused by quantization.

Xiaolin Wu, Xi Zhang, Xiao Shu

Subitizing, or the sense of small natural numbers, is an innate cognitive function of humans and primates; it responds to visual stimuli prior to the development of any symbolic skills, language or arithmetic. Given successes of deep learning (DL) in tasks of visual intelligence and given the primitivity of number sense, a tantalizing question is whether DL can comprehend numbers and perform subitizing. But somewhat disappointingly, extensive experiments of the type of cognitive psychology demonstrate that the examples-driven black box DL cannot see through superficial variations in visual representations and distill the abstract notion of natural number, a task that children perform with high accuracy and confidence. The failure is apparently due to the learning method not the CNN computational machinery itself. A recurrent neural network capable of subitizing does exist, which we construct by encoding a mechanism of mathematical morphology into the CNN convolutional kernels. Also, we investigate, using subitizing as a test bed, the ways to aid the black box DL by cognitive priors derived from human insight. Our findings are mixed and interesting, pointing to both cognitive deficit of pure DL, and some measured successes of boosting DL by predetermined cognitive implements. This case study of DL in cognitive computing is meaningful for visual numerosity represents a minimum level of human intelligence.

Zhixiang Chi, Xiaolin Wu, Xiao Shu et al.

Image of a scene captured through a piece of transparent and reflective material, such as glass, is often spoiled by a superimposed layer of reflection image. While separating the reflection from a familiar object in an image is mentally not difficult for humans, it is a challenging, ill-posed problem in computer vision. In this paper, we propose a novel deep convolutional encoder-decoder method to remove the objectionable reflection by learning a map between image pairs with and without reflection. For training the neural network, we model the physical formation of reflections in images and synthesize a large number of photo-realistic reflection-tainted images from reflection-free images collected online. Extensive experimental results show that, although the neural network learns only from synthetic data, the proposed method is effective on real-world images, and it significantly outperforms the other tested state-of-the-art techniques.

Xi Zhang, Xiaolin Wu

Recently a number of CNN-based techniques were proposed to remove image compression artifacts. As in other restoration applications, these techniques all learn a mapping from decompressed patches to the original counterparts under the ubiquitous $\ell_\infty$ metric. However, this approach is incapable of restoring distinctive image details which may be statistical outliers but have high semantic importance (e.g., tiny lesions in medical images). To overcome this weakness, we propose to incorporate an $\ell_\infty$ fidelity criterion in the design of neural network so that no small, distinctive structures of the original image can be dropped or distorted. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in $\ell_\infty$ error metric and perceptual quality, while being competitive in $\ell_2$ error metric as well. It can restore subtle image details that are otherwise destroyed or missed by other algorithms. Our research suggests a new machine learning paradigm of ultra high fidelity image compression that is ideally suited for applications in medicine, space, and sciences.

Bolin Liu, Xiao Shu, Xiaolin Wu

This paper presents a generic pre-processor for expediting conventional template matching techniques. Instead of locating the best matched patch in the reference image to a query template via exhaustive search, the proposed algorithm rules out regions with no possible matches with minimum computational efforts. While working on simple patch features, such as mean, variance and gradient, the fast pre-screening is highly discriminative. Its computational efficiency is gained by using a novel octagonal-star-shaped template and the inclusion-exclusion principle to extract and compare patch features. Moreover, it can handle arbitrary rotation and scaling of reference images effectively. Extensive experiments demonstrate that the proposed algorithm greatly reduces the search space while never missing the best match.

Xiaolin Wu, Xi Zhang, Chang Liu

This article is a sequel to our earlier work [25]. The main objective of our research is to explore the potential of supervised machine learning in face-induced social computing and cognition, riding on the momentum of much heralded successes of face processing, analysis and recognition on the tasks of biometric-based identification. We present a case study of automated statistical inference on sociopsychological perceptions of female faces controlled for race, attractiveness, age and nationality. Our empirical evidences point to the possibility of training machine learning algorithms, using example face images characterized by internet users, to predict perceptions of personality traits and demeanors.

Xiaolin Wu, Xi Zhang

In November 2016 we submitted to arXiv our paper "Automated Inference on Criminality Using Face Images". It generated a great deal of discussions in the Internet and some media outlets. Our work is only intended for pure academic discussions; how it has become a media consumption is a total surprise to us. Although in agreement with our critics on the need and importance of policing AI research for the general good of the society, we are deeply baffled by the ways some of them mispresented our work, in particular the motive and objective of our research.

Xianming Liu, Gene Cheung, Xiaolin Wu et al.

Given the prevalence of JPEG compressed images, optimizing image reconstruction from the compressed format remains an important problem. Instead of simply reconstructing a pixel block from the centers of indexed DCT coefficient quantization bins (hard decoding), soft decoding reconstructs a block by selecting appropriate coefficient values within the indexed bins with the help of signal priors. The challenge thus lies in how to define suitable priors and apply them effectively. In this paper, we combine three image priors---Laplacian prior for DCT coefficients, sparsity prior and graph-signal smoothness prior for image patches---to construct an efficient JPEG soft decoding algorithm. Specifically, we first use the Laplacian prior to compute a minimum mean square error (MMSE) initial solution for each code block. Next, we show that while the sparsity prior can reduce block artifacts, limiting the size of the over-complete dictionary (to lower computation) would lead to poor recovery of high DCT frequencies. To alleviate this problem, we design a new graph-signal smoothness prior (desired signal has mainly low graph frequencies) based on the left eigenvectors of the random walk graph Laplacian matrix (LERaG). Compared to previous graph-signal smoothness priors, LERaG has desirable image filtering properties with low computation overhead. We demonstrate how LERaG can facilitate recovery of high DCT frequencies of a piecewise smooth (PWS) signal via an interpretation of low graph frequency components as relaxed solutions to normalized cut in spectral clustering. Finally, we construct a soft decoding algorithm using the three signal priors with appropriate prior weights. Experimental results show that our proposal outperforms state-of-the-art soft decoding algorithms in both objective and subjective evaluations noticeably.

Xiao Shu, Xiaolin Wu

Small compression noises, despite being transparent to human eyes, can adversely affect the results of many image restoration processes, if left unaccounted for. Especially, compression noises are highly detrimental to inverse operators of high-boosting (sharpening) nature, such as deblurring and superresolution against a convolution kernel. By incorporating the non-linear DCT quantization mechanism into the formulation for image restoration, we propose a new sparsity-based convex programming approach for joint compression noise removal and image restoration. Experimental results demonstrate significant performance gains of the new approach over existing image restoration methods.

Reza Pournaghi, Xiaolin Wu

High frame video (HFV) is an important investigational tool in sciences, engineering and military. In ultra-high speed imaging, the obtainable temporal, spatial and spectral resolutions are limited by the sustainable throughput of in-camera mass memory, the lower bound of exposure time, and illumination conditions. In order to break these bottlenecks, we propose a new coded video acquisition framework that employs K > 2 conventional cameras, each of which makes random measurements of the 3D video signal in both temporal and spatial domains. For each of the K cameras, this multi-camera strategy greatly relaxes the stringent requirements in memory speed, shutter speed, and illumination strength. The recovery of HFV from these random measurements is posed and solved as a large scale l1 minimization problem by exploiting joint temporal and spatial sparsities of the 3D signal. Three coded video acquisition techniques of varied trade offs between performance and hardware complexity are developed: frame-wise coded acquisition, pixel-wise coded acquisition, and column-row-wise coded acquisition. The performances of these techniques are analyzed in relation to the sparsity of the underlying video signal. Simulations of these new HFV capture techniques are carried out and experimental results are reported.