Network quantization generally converts full-precision weights and/or activations into low-bit fixed-point values in order to accelerate an inference process. Recent approaches to network quantization further discretize the gradients into low-bit fixed-point values, enabling an efficient training. They typically set a quantization interval using a min-max range of the gradients or adjust the interval such that the quantization error for entire gradients is minimized. In this paper, we analyze the quantization error of gradients for the low-bit fixed-point training, and show that lowering the error for large-magnitude gradients boosts the quantization performance significantly. Based on this, we derive an upper bound of quantization error for the large gradients in terms of the quantization interval, and obtain an optimal condition for the interval minimizing the quantization error for large gradients. We also introduce an interval update algorithm that adjusts the quantization interval adaptively to maintain a small quantization error for large gradients. Experimental results demonstrate the effectiveness of our quantization method for various combinations of network architectures and bit-widths on various tasks, including image classification, object detection, and super-resolution.
Deconvolution with a box (square wave) is a key operation for super-resolution with pixel-shift cameras. In general convolution with a box is not invertible. However, we can obtain perfect reconstructions of sparse signals using convex optimization. We give a direct proof that improves on the reconstruction bound that follows from previous results. We also show our bound is tight and matches an information theoretic limit.
Updated building footprints with refugee camps from high-resolution satellite imagery can support related humanitarian operations. This study explores the utilization of the "Segment Anything Model" (SAM) and one of its branches, SAM-Adapter, for semantic segmentation tasks in the building extraction from satellite imagery. SAM-Adapter is a lightweight adaptation of the SAM and emerges as a powerful tool for this extraction task across diverse refugee camps. Our research proves that SAM-Adapter excels in scenarios where data availability is limited compared to other classic (e.g., U-Net) or advanced semantic segmentation models (e.g., Transformer). Furthermore, the impact of upscaling techniques on model performance is highlighted, with methods like super-resolution (SR) models proving invaluable for improving model performance. Additionally, the study unveils intriguing phenomena, including the model's rapid convergence in the first training epoch when using upscaled image data for training, suggesting opportunities for future research. The codes covering each step from data preparation, model training, model inferencing, and the generation of Shapefiles for predicted masks are available on a GitHub repository to benefit the extended scientific community and humanitarian operations.
Diffusion models have emerged as powerful generative techniques for solving inverse problems. Despite their success in a variety of inverse problems in imaging, these models require many steps to converge, leading to slow inference time. Recently, there has been a trend in diffusion models for employing sophisticated noise schedules that involve more frequent iterations of timesteps at lower noise levels, thereby improving image generation and convergence speed. However, application of these ideas for solving inverse problems with diffusion models remain challenging, as these noise schedules do not perform well when using empirical tuning for the forward model log-likelihood term weights. To tackle these challenges, we propose zero-shot approximate posterior sampling (ZAPS) that leverages connections to zero-shot physics-driven deep learning. ZAPS fixes the number of sampling steps, and uses zero-shot training with a physics-guided loss function to learn log-likelihood weights at each irregular timestep. We apply ZAPS to the recently proposed diffusion posterior sampling method as baseline, though ZAPS can also be used with other posterior sampling diffusion models. We further approximate the Hessian of the logarithm of the prior using a diagonalization approach with learnable diagonal entries for computational efficiency. These parameters are optimized over a fixed number of epochs with a given computational budget. Our results for various noisy inverse problems, including Gaussian and motion deblurring, inpainting, and super-resolution show that ZAPS reduces inference time, provides robustness to irregular noise schedules and improves reconstruction quality. Code is available at https://github.com/ualcalar17/ZAPS
Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and computational complexity. In this paper, we first describe a strong baseline for AVSR by putting together three variants of elementary building blocks: 1) a flow-guided recurrent unit that aggregates spatiotemporal information from previous frames, 2) a flow-refined cross-attention unit that selects spatiotemporal information from future frames, and 3) a hyper-upsampling unit that generates scaleaware and content-independent upsampling kernels. We then introduce ST-AVSR by equipping our baseline with a multi-scale structural and textural prior computed from the pre-trained VGG network. This prior has proven effective in discriminating structure and texture across different locations and scales, which is beneficial for AVSR. Comprehensive experiments show that ST-AVSR significantly improves super-resolution quality, generalization ability, and inference speed over the state-of-theart. The code is available at https://github.com/shangwei5/ST-AVSR.
Recently, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks such as image super-resolution and denoising. Despite their remarkable performance, the backdoor vulnerability of I2I networks has not been explored. To fill this research gap, we conduct a comprehensive investigation on the susceptibility of I2I networks to backdoor attacks. Specifically, we propose a novel backdoor attack technique, where the compromised I2I network behaves normally on clean input images, yet outputs a predefined image of the adversary for malicious input images containing the trigger. To achieve this I2I backdoor attack, we propose a targeted universal adversarial perturbation (UAP) generation algorithm for I2I networks, where the generated UAP is used as the backdoor trigger. Additionally, in the backdoor training process that contains the main task and the backdoor task, multi-task learning (MTL) with dynamic weighting methods is employed to accelerate convergence rates. In addition to attacking I2I tasks, we extend our I2I backdoor to attack downstream tasks, including image classification and object detection. Extensive experiments demonstrate the effectiveness of the I2I backdoor on state-of-the-art I2I network architectures, as well as the robustness against different mainstream backdoor defenses.
Transformer-based methods have demonstrated impressive results in medical image restoration, attributed to the multi-head self-attention (MSA) mechanism in the spatial dimension. However, the majority of existing Transformers conduct attention within fixed and coarsely partitioned regions (\text{e.g.} the entire image or fixed patches), resulting in interference from irrelevant regions and fragmentation of continuous image content. To overcome these challenges, we introduce a novel Region Attention Transformer (RAT) that utilizes a region-based multi-head self-attention mechanism (R-MSA). The R-MSA dynamically partitions the input image into non-overlapping semantic regions using the robust Segment Anything Model (SAM) and then performs self-attention within these regions. This region partitioning is more flexible and interpretable, ensuring that only pixels from similar semantic regions complement each other, thereby eliminating interference from irrelevant regions. Moreover, we introduce a focal region loss to guide our model to adaptively focus on recovering high-difficulty regions. Extensive experiments demonstrate the effectiveness of RAT in various medical image restoration tasks, including PET image synthesis, CT image denoising, and pathological image super-resolution. Code is available at \href{https://github.com/Yaziwel/Region-Attention-Transformer-for-Medical-Image-Restoration.git}{https://github.com/RAT}.
Super-resolution reconstruction is aimed at generating images of high spatial resolution from low-resolution observations. State-of-the-art super-resolution techniques underpinned with deep learning allow for obtaining results of outstanding visual quality, but it is seldom verified whether they constitute a valuable source for specific computer vision applications. In this paper, we investigate the possibility of employing super-resolution as a preprocessing step to improve optical character recognition from document scans. To achieve that, we propose to train deep networks for single-image super-resolution in a task-driven way to make them better adapted for the purpose of text detection. As problems limited to a specific task are heavily ill-posed, we introduce a multi-task loss function that embraces components related with text detection coupled with those guided by image similarity. The obtained results reported in this paper are encouraging and they constitute an important step towards real-world super-resolution of document images.
By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose a convolutional neural network (CNN) for space-time video super-resolution, namely GIRNet. To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module. In the feature-level temporal interpolation module, we leverage deformable convolution, which adapts to deformations and scale variations of objects across different scene locations. This presents a more efficient solution than conventional convolution for extracting features from moving objects. Our network effectively uses forward and backward feature information to determine inter-frame offsets, leading to the direct generation of interpolated frame features. In the global spatial-temporal information-based residual convLSTM module, the first convLSTM is used to derive global spatial-temporal information from the input features, and the second convLSTM uses the previously computed global spatial-temporal information feature as its initial cell state. This second convLSTM adopts residual connections to preserve spatial information, thereby enhancing the output features. Experiments on the Vimeo90K dataset show that the proposed method outperforms state-of-the-art techniques in peak signal-to-noise-ratio (by 1.45 dB, 1.14 dB, and 0.02 dB over STARnet, TMNet, and 3DAttGAN, respectively), structural similarity index(by 0.027, 0.023, and 0.006 over STARnet, TMNet, and 3DAttGAN, respectively), and visually.
This paper focuses on the dataset-free Blind Image Super-Resolution (BISR). Unlike existing dataset-free BISR methods that focus on obtaining a degradation kernel for the entire image, we are the first to explicitly design a spatially-variant degradation model for each pixel. Our method also benefits from having a significantly smaller number of learnable parameters compared to data-driven spatially-variant BISR methods. Concretely, each pixel's degradation kernel is expressed as a linear combination of a learnable dictionary composed of a small number of spatially-variant atom kernels. The coefficient matrices of the atom degradation kernels are derived using membership functions of fuzzy set theory. We construct a novel Probabilistic BISR model with tailored likelihood function and prior terms. Subsequently, we employ the Monte Carlo EM algorithm to infer the degradation kernels for each pixel. Our method achieves a significant improvement over other state-of-the-art BISR methods, with an average improvement of 1 dB (2x).Code will be released at https://github.com/shaojieguoECNU/SVDSR.
We present VEnhancer, a generative space-time enhancement framework that improves the existing text-to-video results by adding more details in spatial domain and synthetic detailed motion in temporal domain. Given a generated low-quality video, our approach can increase its spatial and temporal resolution simultaneously with arbitrary up-sampling space and time scales through a unified video diffusion model. Furthermore, VEnhancer effectively removes generated spatial artifacts and temporal flickering of generated videos. To achieve this, basing on a pretrained video diffusion model, we train a video ControlNet and inject it to the diffusion model as a condition on low frame-rate and low-resolution videos. To effectively train this video ControlNet, we design space-time data augmentation as well as video-aware conditioning. Benefiting from the above designs, VEnhancer yields to be stable during training and shares an elegant end-to-end training manner. Extensive experiments show that VEnhancer surpasses existing state-of-the-art video super-resolution and space-time super-resolution methods in enhancing AI-generated videos. Moreover, with VEnhancer, exisiting open-source state-of-the-art text-to-video method, VideoCrafter-2, reaches the top one in video generation benchmark -- VBench.
Standard single-image super-resolution creates paired training data from high-resolution images through fixed downsampling kernels. However, real-world super-resolution (RWSR) faces unknown degradations in the low-resolution inputs, all the while lacking paired training data. Existing methods approach this problem by learning blind general models through complex synthetic augmentations on training inputs; they sacrifice the performance on specific degradation for broader generalization to many possible ones. We address the unsupervised RWSR for a targeted real-world degradation. We study from a distillation perspective and introduce a novel pairwise distance distillation framework. Through our framework, a model specialized in synthetic degradation adapts to target real-world degradations by distilling intra- and inter-model distances across the specialized model and an auxiliary generalized model. Experiments on diverse datasets demonstrate that our method significantly enhances fidelity and perceptual quality, surpassing state-of-the-art approaches in RWSR. The source code is available at https://github.com/Yuehan717/PDD.
Image segmentation is fundamental task for medical image analysis, whose accuracy is improved by the development of neural networks. However, the existing algorithms that achieve high-resolution performance require high-resolution input, resulting in substantial computational expenses and limiting their applicability in the medical field. Several studies have proposed dual-stream learning frameworks incorporating a super-resolution task as auxiliary. In this paper, we rethink these frameworks and reveal that the feature similarity between tasks is insufficient to constrain vessels or lesion segmentation in the medical field, due to their small proportion in the image. To address this issue, we propose a DS2F (Dual-Stream Shared Feature) framework, including a Shared Feature Extraction Module (SFEM). Specifically, we present Multi-Scale Cross Gate (MSCG) utilizing multi-scale features as a novel example of SFEM. Then we define a proxy task and proxy loss to enable the features focus on the targets based on the assumption that a limited set of shared features between tasks is helpful for their performance. Extensive experiments on six publicly available datasets across three different scenarios are conducted to verify the effectiveness of our framework. Furthermore, various ablation studies are conducted to demonstrate the significance of our DS2F.
Deep learning-based (DL-based) hyperspectral image (HIS) super-resolution (SR) methods have achieved remarkable performance and attracted attention in industry and academia. Nonetheless, most current methods explored and learned the mapping relationship between low-resolution (LR) and high-resolution (HR) HSIs, leading to the side effect of increasing unreliability and irrationality in solving the ill-posed SR problem. We find, quite interestingly, LR imaging is similar to the mixed pixel phenomenon. A single photodetector in sensor arrays receives the reflectance signals reflected by a number of classes, resulting in low spatial resolution and mixed pixel problems. Inspired by this observation, this paper proposes a component-aware HSI SR network called UnmixingSR, in which the unsupervised HU as an auxiliary task is used to perceive the material components of HSIs. We regard HU as an auxiliary task and incorporate it into the HSI SR process by exploring the constraints between LR and HR abundances. Instead of only learning the mapping relationship between LR and HR HSIs, we leverage the bond between LR abundances and HR abundances to boost the stability of our method in solving SR problems. Moreover, the proposed unmixing process can be embedded into existing deep SR models as a plug-in-play auxiliary task. Experimental results on hyperspectral experiments show that unmixing process as an auxiliary task incorporated into the SR problem is feasible and rational, achieving outstanding performance. The code is available at
Super-resolution ultrasound imaging through microbubble (MB) localisation and tracking, also known as ultrasound localisation microscopy, allows non-invasive sub-diffraction resolution imaging of microvasculature in animals and humans. The number of MBs localised from the acquired contrast-enhanced ultrasound (CEUS) images and the localisation precision directly influence the quality of the resulting super-resolution microvasculature images. However, non-negligible noise present in the CEUS images can make localising MBs challenging. To enhance the MB localisation performance, we propose a Multi-Frame Deconvolution (MF-Decon) framework that can exploit the spatiotemporal coherence inherent in the CEUS data, with new spatial and temporal regularisers designed based on total variation (TV) and regularisation by denoising (RED). Based on the MF-Decon framework, we introduce two novel methods: MF-Decon with spatial and temporal TVs (MF-Decon+3DTV) and MF-Decon with spatial RED and temporal TV (MF-Decon+RED+TV). Results from in silico simulations indicate that our methods outperform two widely used methods using deconvolution or normalised cross-correlation across all evaluation metrics, including precision, recall, $F_1$ score, mean and standard localisation errors. In particular, our methods improve MB localisation precision by up to 39% and recall by up to 12%. Super-resolution microvasculature maps generated with our methods on a publicly available in vivo rat brain dataset show less noise, better contrast, higher resolution and more vessel structures.
Neuromorphic imaging is an emerging technique that imitates the human retina to sense variations in dynamic scenes. It responds to pixel-level brightness changes by asynchronous streaming events and boasts microsecond temporal precision over a high dynamic range, yielding blur-free recordings under extreme illumination. Nevertheless, this modality falls short in spatial resolution and leads to a low level of visual richness and clarity. Pursuing hardware upgrades is expensive and might cause compromised performance due to more burdens on computational requirements. Another option is to harness offline, plug-in-play super-resolution solutions. However, existing ones, which demand substantial sample volumes for lengthy training on massive computing resources, are largely restricted by real data availability owing to the current imperfect high-resolution devices, as well as the randomness and variability of motion. To tackle these challenges, we introduce the first self-supervised neuromorphic super-resolution prototype. It can be self-adaptive to per input source from any low-resolution camera to estimate an optimal, high-resolution counterpart of any scale, without the need of side knowledge and prior training. Evaluated on downstream tasks, such a simple yet effective method can obtain competitive results against the state-of-the-arts, significantly promoting flexibility but not sacrificing accuracy. It also delivers enhancements for inferior natural images and optical micrographs acquired under non-ideal imaging conditions, breaking through the limitations that are challenging to overcome with frame-based techniques. In the current landscape where the use of high-resolution cameras for event-based sensing remains an open debate, our solution is a cost-efficient and practical alternative, paving the way for more intelligent imaging systems.
Fusing hyperspectral images (HSIs) with multispectral images (MSIs) has become a mainstream approach to enhance the spatial resolution of HSIs. Many HSI-MSI fusion methods have achieved impressive results. Nevertheless, certain challenges persist, including: (a) A majority of current methods rely on accurate registration of HSI and MSI, which can be challenging in real-world applications.(b) The obtained HSI-MSI pairs may not be fully utilized. In this paper, we propose a hybrid registration and fusion constrained optimization model named RAF-NLRGS. With respect to challenge (a), the RAF model integrates batch image alignment within the fusion process, facilitating simultaneous execution of image registration and fusion. To address issue (b), the NLRGS model incorporates a nonconvex low-rank and group-sparse structure, leveraging group sparsity to effectively harness valuable information embedded in the residual data. Moreover, the NLRGS model can further enhance fusion performance based on the RAF model. Subsequently, the RAF-NLRGS model is solved within the framework of Generalized Gauss-Newton (GGN) algorithm and Proximal Alternating Optimization (PAO) algorithm. Theoretically, we establish the error bounds for the NLRGS model and the convergence analysis of corresponding algorithms is also presented. Finally, extensive numerical experiments on HSI datasets are conducted to verify the effectiveness of our method.
In this paper, we propose to reformulate the blind image deblurring task to directly learn an inverse of the degradation model using a deep linear network. We introduce Deep Identity Learning (DIL), a novel learning strategy that includes a dedicated regularization term based on the properties of linear systems, to exploit the identity relation between the degradation and inverse degradation models. The salient aspect of our proposed framework is it neither relies on a deblurring dataset nor a single input blurred image (like Polyblur, a self-supervised method). Since it is purely image-data-independent, we term our model as Null-Shot deblurring Using Deep Identity Learning (NSD-DIL). We also provide an explicit representation of the learned deep linear network in a matrix form, called Deep Restoration Kernel (DRK) for deblurring task. The proposed framework detours the typical degradation kernel estimation step involved in most of the existing blind deblurring solutions by the proposition of our Random Kernel Gallery (RKG) dataset. In this work, we focus on the restoration of mild blur images, generated by small out-of-focus, lens blur, or slight camera motion, which often occurs in real images. Our experiments show that the proposed method outperforms both traditional and deep learning based deblurring methods, with at least an order of 100 lesser computational resources. The proposed NSD-DIL method can be effortlessly extended to the Image Super-Resolution (ISR) task as well to restore the low-resolution images with fine details. The NSD-DIL model and its kernel form representation (DRK) are lightweight yet robust and restore the mild blur input in a fraction of a second. Hence, more suitable for wide real-time applications.
In this paper, we propose a self-prior guided Mamba-UNet network (SMamba-UNet) for medical image super-resolution. Existing methods are primarily based on convolutional neural networks (CNNs) or Transformers. CNNs-based methods fail to capture long-range dependencies, while Transformer-based approaches face heavy calculation challenges due to their quadratic computational complexity. Recently, State Space Models (SSMs) especially Mamba have emerged, capable of modeling long-range dependencies with linear computational complexity. Inspired by Mamba, our approach aims to learn the self-prior multi-scale contextual features under Mamba-UNet networks, which may help to super-resolve low-resolution medical images in an efficient way. Specifically, we obtain self-priors by perturbing the brightness inpainting of the input image during network training, which can learn detailed texture and brightness information that is beneficial for super-resolution. Furthermore, we combine Mamba with Unet network to mine global features at different levels. We also design an improved 2D-Selective-Scan (ISS2D) module to divide image features into different directional sequences to learn long-range dependencies in multiple directions, and adaptively fuse sequence information to enhance super-resolved feature representation. Both qualitative and quantitative experimental results demonstrate that our approach outperforms current state-of-the-art methods on two public medical datasets: the IXI and fastMRI.
In this paper, we propose a new architecture, called Deform-Mamba, for MR image super-resolution. Unlike conventional CNN or Transformer-based super-resolution approaches which encounter challenges related to the local respective field or heavy computational cost, our approach aims to effectively explore the local and global information of images. Specifically, we develop a Deform-Mamba encoder which is composed of two branches, modulated deform block and vision Mamba block. We also design a multi-view context module in the bottleneck layer to explore the multi-view contextual content. Thanks to the extracted features of the encoder, which include content-adaptive local and efficient global information, the vision Mamba decoder finally generates high-quality MR images. Moreover, we introduce a contrastive edge loss to promote the reconstruction of edge and contrast related content. Quantitative and qualitative experimental results indicate that our approach on IXI and fastMRI datasets achieves competitive performance.