High anisotropy in volumetric medical images can lead to the inconsistent quantification of anatomical and pathological structures. Particularly in optical coherence tomography (OCT), slice spacing can substantially vary across and within datasets, studies, and clinical practices. We propose to standardize OCT volumes to less anisotropic volumes by conditioning 3D diffusion models with en face scanning laser ophthalmoscopy (SLO) imaging data, a 2D modality already commonly available in clinical practice. We trained and evaluated on data from the multicenter and multimodal MACUSTAR study. While upsampling the number of slices by a factor of 8, our method outperforms tricubic interpolation and diffusion models without en face conditioning in terms of perceptual similarity metrics. Qualitative results demonstrate improved coherence and structural similarity. Our approach allows for better informed generative decisions, potentially reducing hallucinations. We hope this work will provide the next step towards standardized high-quality volumetric imaging, enabling more consistent quantifications.
The skull segmentation from CT scans can be seen as an already solved problem. However, in MR this task has a significantly greater complexity due to the presence of soft tissues rather than bones. Capturing the bone structures from MR images of the head, where the main visualization objective is the brain, is very demanding. The attempts that make use of skull stripping seem to not be well suited for this task and fail to work in many cases. On the other hand, supervised approaches require costly and time-consuming skull annotations. To overcome the difficulties we propose a fully unsupervised approach, where we do not perform the segmentation directly on MR images, but we rather perform a synthetic CT data generation via MR-to-CT translation and perform the segmentation there. We address many issues associated with unsupervised skull segmentation including the unpaired nature of MR and CT datasets (contrastive learning), low resolution and poor quality (super-resolution), and generalization capabilities. The research has a significant value for downstream tasks requiring skull segmentation from MR volumes such as craniectomy or surgery planning and can be seen as an important step towards the utilization of synthetic data in medical imaging.
Most existing super-resolution methods and datasets have been developed to improve the image quality in well-lighted conditions. However, these methods do not work well in real-world low-light conditions as the images captured in such conditions lose most important information and contain significant unknown noises. To solve this problem, we propose a SRRIIE dataset with an efficient conditional diffusion probabilistic models-based method. The proposed dataset contains 4800 paired low-high quality images. To ensure that the dataset are able to model the real-world image degradation in low-illumination environments, we capture images using an ILDC camera and an optical zoom lens with exposure levels ranging from -6 EV to 0 EV and ISO levels ranging from 50 to 12800. We comprehensively evaluate with various reconstruction and perceptual metrics and demonstrate the practicabilities of the SRRIIE dataset for deep learning-based methods. We show that most existing methods are less effective in preserving the structures and sharpness of restored images from complicated noises. To overcome this problem, we revise the condition for Raw sensor data and propose a novel time-melding condition for diffusion probabilistic model. Comprehensive quantitative and qualitative experimental results on the real-world benchmark datasets demonstrate the feasibility and effectivenesses of the proposed conditional diffusion probabilistic model on Raw sensor data. Code and dataset will be available at https://github.com/Yaofang-Liu/Super-Resolving
Real-world image super-resolution (Real-ISR) aims at restoring high-quality (HQ) images from low-quality (LQ) inputs corrupted by unknown and complex degradations. In particular, pretrained text-to-image (T2I) diffusion models provide strong generative priors to reconstruct credible and intricate details. However, T2I generation focuses on semantic consistency while Real-ISR emphasizes pixel-level reconstruction, which hinders existing methods from fully exploiting diffusion priors. To address this challenge, we introduce ConsisSR to handle both semantic and pixel-level consistency. Specifically, compared to coarse-grained text prompts, we exploit the more powerful CLIP image embedding and effectively leverage both modalities through our Hybrid Prompt Adapter (HPA) for semantic guidance. Secondly, we introduce Time-aware Latent Augmentation (TALA) to mitigate the inherent gap between T2I generation and Real-ISR consistency requirements. By randomly mixing LQ and HQ latent inputs, our model not only handle timestep-specific diffusion noise but also refine the accumulated latent representations. Last but not least, our GAN-Embedding strategy employs the pretrained Real-ESRGAN model to refine the diffusion start point. This accelerates the inference process to 10 steps while preserving sampling quality, in a training-free manner.Our method demonstrates state-of-the-art performance among both full-scale and accelerated models. The code will be made publicly available.
Intelligent processing and analysis of satellite video has become one of the research hotspots in the representation of remote sensing, and satellite video super-resolution (SVSR) is an important research direction which can improve the image quality of satellite video. However, existing approaches for SVSR often underutilize a notable advantage inherent to satellite video: the presence of extensive sequential imagery capturing a consistent scene. Presently, the majority of SVSR methods merely harness a limited number of adjacent frames for enhancing the resolution of individual frames, thus resulting in suboptimal information utilization. In response, we introduce the Recurrent Aggregation Network for Satellite Video Super-Resolution (RASVSR). This innovative framework leverages a bidirectional recurrent neural network to propagate extracted features from each frame across the entire video sequence. It relies on an alignment method based on optical flow and deformable convolution (DCN) to realize the alignment of the features, and a Temporal Feature Fusion Module (TFF) to realize effective feature fusion over time. Notably, our research underscores the positive influence of employing lengthier image sequences in SVSR. In the context of RASVSR, with better alignment and fusion, we make the perceptual field of each frame spanning 100 frames of the video, thus acquiring richer information, and information between different images can be complementary. This strategic approach culminates in superior performance compared to alternative methods, as evidenced by a noteworthy 1.15 dB improvement in PSNR, with very few parameters.
Super-resolution (SR) is a promising cost-effective downscaling methodology for producing high-resolution climate information from coarser counterparts. A particular application is downscaling regional reanalysis outputs (predictand) from the driving global counterparts (predictor). This study conducts an intercomparison of various SR downscaling methods focusing on temperature and using the CERRA reanalysis (5.5 km resolution, produced with a regional atmospheric model driven by ERA5) as example. The method proposed in this work is the Swin transformer and two alternative methods are used as benchmark (fully convolutional U-Net and convolutional and dense DeepESD) as well as the simple bicubic interpolation. We compare two approaches, the standard one using the full domain as input and a more scalable tiling approach, dividing the full domain into tiles that are used as input. The methods are trained to downscale CERRA surface temperature, based on temperature information from the driving ERA5; in addition, the tiling approach includes static orographic information. We show that the tiling approach, which requires spatial transferability, comes at the cost of a lower performance (although it outperforms some full-domain benchmarks), but provides an efficient scalable solution that allows SR reduction on a pan-European scale and is valuable for real-time applications.
Recent RGB-guided depth super-resolution methods have achieved impressive performance under the assumption of fixed and known degradation (e.g., bicubic downsampling). However, in real-world scenarios, captured depth data often suffer from unconventional and unknown degradation due to sensor limitations and complex imaging environments (e.g., low reflective surfaces, varying illumination). Consequently, the performance of these methods significantly declines when real-world degradation deviate from their assumptions. In this paper, we propose the Degradation Oriented and Regularized Network (DORNet), a novel framework designed to adaptively address unknown degradation in real-world scenes through implicit degradation representations. Our approach begins with the development of a self-supervised degradation learning strategy, which models the degradation representations of low-resolution depth data using routing selection-based degradation regularization. To facilitate effective RGB-D fusion, we further introduce a degradation-oriented feature transformation module that selectively propagates RGB content into the depth data based on the learned degradation priors. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our DORNet in handling unknown degradation, outperforming existing methods. The code is available at https://github.com/yanzq95/DORNet.
Omnidirectional video (ODV) can provide an immersive experience and is widely utilized in the field of virtual reality and augmented reality. However, the restricted capturing devices and transmission bandwidth lead to the low resolution of ODVs. Video super-resolution (VSR) methods are proposed to enhance the resolution of videos, but ODV projection distortions in the application are not well addressed directly applying such methods. To achieve better super-resolution reconstruction quality, we propose a novel Spatio-Temporal Distortion Aware Network (STDAN) oriented to ODV characteristics. Specifically, a spatio-temporal distortion modulation module is introduced to improve spatial ODV projection distortions and exploit the temporal correlation according to intra and inter alignments. Next, we design a multi-frame reconstruction and fusion mechanism to refine the consistency of reconstructed ODV frames. Furthermore, we incorporate latitude-saliency adaptive maps in the loss function to concentrate on important viewpoint regions with higher texture complexity and human-watching interest. In addition, we collect a new ODV-SR dataset with various scenarios. Extensive experimental results demonstrate that the proposed STDAN achieves superior super-resolution performance on ODVs and outperforms state-of-the-art methods.
State Space Models (SSM), such as Mamba, have shown strong representation ability in modeling long-range dependency with linear complexity, achieving successful applications from high-level to low-level vision tasks. However, SSM's sequential nature necessitates multiple scans in different directions to compensate for the loss of spatial dependency when unfolding the image into a 1D sequence. This multi-direction scanning strategy significantly increases the computation overhead and is unbearable for high-resolution image processing. To address this problem, we propose a novel Hierarchical Mamba network, namely, Hi-Mamba, for image super-resolution (SR). Hi-Mamba consists of two key designs: (1) The Hierarchical Mamba Block (HMB) assembled by a Local SSM (L-SSM) and a Region SSM (R-SSM) both with the single-direction scanning, aggregates multi-scale representations to enhance the context modeling ability. (2) The Direction Alternation Hierarchical Mamba Group (DA-HMG) allocates the isomeric single-direction scanning into cascading HMBs to enrich the spatial relationship modeling. Extensive experiments demonstrate the superiority of Hi-Mamba across five benchmark datasets for efficient SR. For example, Hi-Mamba achieves a significant PSNR improvement of 0.29 dB on Manga109 for $\times3$ SR, compared to the strong lightweight MambaIR.
Recently, lightweight methods for single image super-resolution (SISR) have gained significant popularity and achieved impressive performance due to limited hardware resources. These methods demonstrate that adopting residual feature distillation is an effective way to enhance performance. However, we find that using residual connections after each block increases the model's storage and computational cost. Therefore, to simplify the network structure and learn higher-level features and relationships between features, we use depthwise separable convolutions, fully connected layers, and activation functions as the basic feature extraction modules. This significantly reduces computational load and the number of parameters while maintaining strong feature extraction capabilities. To further enhance model performance, we propose the Hybrid Attention Separable Block (HASB), which combines channel attention and spatial attention, thus making use of their complementary advantages. Additionally, we use depthwise separable convolutions instead of standard convolutions, significantly reducing the computational load and the number of parameters while maintaining strong feature extraction capabilities. During the training phase, we also adopt a warm-start retraining strategy to exploit the potential of the model further. Extensive experiments demonstrate the effectiveness of our approach. Our method achieves a smaller model size and reduced computational complexity without compromising performance. Code can be available at https://github.com/nathan66666/HASN.git
High-resolution (HR) 3D magnetic resonance imaging (MRI) can provide detailed anatomical structural information, enabling precise segmentation of regions of interest for various medical image analysis tasks. Due to the high demands of acquisition device, collection of HR images with their annotations is always impractical in clinical scenarios. Consequently, segmentation results based on low-resolution (LR) images with large slice thickness are often unsatisfactory for subsequent tasks. In this paper, we propose a novel Resource-Efficient High-Resolution Segmentation framework (REHRSeg) to address the above-mentioned challenges in real-world applications, which can achieve HR segmentation while only employing the LR images as input. REHRSeg is designed to leverage self-supervised super-resolution (self-SR) to provide pseudo supervision, therefore the relatively easier-to-acquire LR annotated images generated by 2D scanning protocols can be directly used for model training. The main contribution to ensure the effectiveness in self-SR for enhancing segmentation is three-fold: (1) We mitigate the data scarcity problem in the medical field by using pseudo-data for training the segmentation model. (2) We design an uncertainty-aware super-resolution (UASR) head in self-SR to raise the awareness of segmentation uncertainty as commonly appeared on the ROI boundaries. (3) We align the spatial features for self-SR and segmentation through structural knowledge distillation to enable a better capture of region correlations. Experimental results demonstrate that REHRSeg achieves high-quality HR segmentation without intensive supervision, while also significantly improving the baseline performance for LR segmentation.
The advent of AI has influenced many aspects of human life, from self-driving cars and intelligent chatbots to text-based image and video generation models capable of creating realistic images and videos based on user prompts (text-to-image, image-to-image, and image-to-video). AI-based methods for image and video super resolution, video frame interpolation, denoising, and compression have already gathered significant attention and interest in the industry and some solutions are already being implemented in real-world products and services. However, to achieve widespread integration and acceptance, AI-generated and enhanced content must be visually accurate, adhere to intended use, and maintain high visual quality to avoid degrading the end user's quality of experience (QoE). One way to monitor and control the visual "quality" of AI-generated and -enhanced content is by deploying Image Quality Assessment (IQA) and Video Quality Assessment (VQA) models. However, most existing IQA and VQA models measure visual fidelity in terms of "reconstruction" quality against a pristine reference content and were not designed to assess the quality of "generative" artifacts. To address this, newer metrics and models have recently been proposed, but their performance evaluation and overall efficacy have been limited by datasets that were too small or otherwise lack representative content and/or distortion capacity; and by performance measures that can accurately report the success of an IQA/VQA model for "GenAI". This paper examines the current shortcomings and possibilities presented by AI-generated and enhanced image and video content, with a particular focus on end-user perceived quality. Finally, we discuss open questions and make recommendations for future work on the "GenAI" quality assessment problems, towards further progressing on this interesting and relevant field of research.
Super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, often relying on effective downsampling to generate diverse and realistic training pairs. In this work, we propose a co-learning framework that jointly optimizes a single-step diffusion-based upsampler and a learnable downsampler, enhanced by two discriminators and a cyclic distillation strategy. Our learnable downsampler is designed to better capture realistic degradation patterns while preserving structural details in the LR domain, which is crucial for enhancing SR performance. By leveraging a diffusion-based approach, our model generates diverse LR-HR pairs during training, enabling robust learning across varying degradations. We demonstrate the effectiveness of our method on both general real-world and domain-specific face SR tasks, achieving state-of-the-art performance in both fidelity and perceptual quality. Our approach not only improves efficiency with a single inference step but also ensures high-quality image reconstruction, bridging the gap between synthetic and real-world SR scenarios.
Frequency estimation from measurements corrupted by noise is a fundamental challenge across numerous engineering and scientific fields. Among the pivotal factors shaping the resolution capacity of any frequency estimation technique are noise levels and measurement count. Often constrained by practical limitations, the number of measurements tends to be limited. This work introduces a learning-driven approach focused on predicting forthcoming measurements based on available samples. Subsequently, we demonstrate that we can attain high-resolution frequency estimates by combining provided and predicted measurements. In particular, our findings indicate that using just one-third of the total measurements, the method achieves a performance akin to that obtained with the complete set. Unlike existing learning-based frequency estimators, our approach's output retains full interpretability. This work holds promise for developing energy-efficient systems with reduced sampling requirements, which will benefit various applications.
Integrated sensing and communications (ISAC) is a promising component of 6G networks, fusing communication and radar technologies to facilitate new services. Additionally, the use of extremely large-scale antenna arrays (ELAA) at the ISAC common receiver not only facilitates terahertz-rate communication links but also significantly enhances the accuracy of target detection in radar applications. In practical scenarios, communication scatterers and radar targets often reside in close proximity to the ISAC receiver. This, combined with the use of ELAA, fundamentally alters the electromagnetic characteristics of wireless and radar channels, shifting from far-field planar-wave propagation to near-field spherical wave propagation. Under the far-field planar-wave model, the phase of the array response vector varies linearly with the antenna index. In contrast, in the near-field spherical wave model, this phase relationship becomes nonlinear. This shift presents a fundamental challenge: the widely-used Fourier analysis can no longer be directly applied for target detection and communication channel estimation at the ISAC common receiver. In this work, we propose a feasible solution to address this fundamental issue. Specifically, we demonstrate that there exists a high-dimensional space in which the phase nonlinearity can be expressed as linear. Leveraging this insight, we develop a lifted super-resolution framework that simultaneously performs communication channel estimation and extracts target parameters with high precision.
Deep neural networks trained as image denoisers are widely used as priors for solving imaging inverse problems. While Gaussian denoising is thought sufficient for learning image priors, we show that priors from deep models pre-trained as more general restoration operators can perform better. We introduce Stochastic deep Restoration Priors (ShaRP), a novel method that leverages an ensemble of such restoration models to regularize inverse problems. ShaRP improves upon methods using Gaussian denoiser priors by better handling structured artifacts and enabling self-supervised training even without fully sampled data. We prove ShaRP minimizes an objective function involving a regularizer derived from the score functions of minimum mean square error (MMSE) restoration operators, and theoretically analyze its convergence. Empirically, ShaRP achieves state-of-the-art performance on tasks such as magnetic resonance imaging reconstruction and single-image super-resolution, surpassing both denoiser-and diffusion-model-based methods without requiring retraining.
Reducing latency is a roaring trend in recent super-resolution (SR) research. While recent progress exploits various convolutional blocks, attention modules, and backbones to unlock the full potentials of the convolutional neural network (ConvNet), achieving real-time performance remains a challenge. To this end, we present PlainUSR, a novel framework incorporating three pertinent modifications to expedite ConvNet for efficient SR. For the convolutional block, we squeeze the lighter but slower MobileNetv3 block into a heavier but faster vanilla convolution by reparameterization tricks to balance memory access and calculations. For the attention module, by modulating input with a regional importance map and gate, we introduce local importance-based attention to realize high-order information interaction within a 1-order attention latency. As to the backbone, we propose a plain U-Net that executes channel-wise discriminate splitting and concatenation. In the experimental phase, PlainUSR exhibits impressively low latency, great scalability, and competitive performance compared to both state-of-the-art latency-oriented and quality-oriented methods. In particular, compared to recent NGswin, the PlainUSR-L is 16.4x faster with competitive performance.
Scanning Electron Microscopy (SEM) is pivotal in revealing intricate micro- and nanoscale features across various research fields. However, obtaining high-resolution SEM images presents challenges, including prolonged scanning durations and potential sample degradation due to extended electron beam exposure. This paper addresses these challenges by training and applying a deep learning based super-resolution algorithm. We show that the chosen algorithm is capable of increasing the resolution by a factor of 4, thereby reducing the initial imaging time by a factor of 16. We benchmark our method in terms of visual similarity and similarity metrics on two different materials, a dual-phase steel and a case-hardening steel, improving over standard interpolation methods. Additionally, we introduce an experimental pipeline for the study of rare events in scanning electron micrographs, without losing high-resolution information.
Image super-resolution methods have made significant strides with deep learning techniques and ample training data. However, they face challenges due to inherent misalignment between low-resolution (LR) and high-resolution (HR) pairs in real-world datasets. In this study, we propose a novel plug-and-play module designed to mitigate these misalignment issues by aligning LR inputs with HR images during training. Specifically, our approach involves mimicking a novel LR sample that aligns with HR while preserving the degradation characteristics of the original LR samples. This module seamlessly integrates with any SR model, enhancing robustness against misalignment. Importantly, it can be easily removed during inference, therefore without introducing any parameters on the conventional SR models. We comprehensively evaluate our method on synthetic and real-world datasets, demonstrating its effectiveness across a spectrum of SR models, including traditional CNNs and state-of-the-art Transformers. The source codes will be publicly made available at https://github.com/omarAlezaby/Mimicked_Ali .
Diffusion-based Video Super-Resolution (VSR) is renowned for generating perceptually realistic videos, yet it grapples with maintaining detail consistency across frames due to stochastic fluctuations. The traditional approach of pixel-level alignment is ineffective for diffusion-processed frames because of iterative disruptions. To overcome this, we introduce SeeClear--a novel VSR framework leveraging conditional video generation, orchestrated by instance-centric and channel-wise semantic controls. This framework integrates a Semantic Distiller and a Pixel Condenser, which synergize to extract and upscale semantic details from low-resolution frames. The Instance-Centric Alignment Module (InCAM) utilizes video-clip-wise tokens to dynamically relate pixels within and across frames, enhancing coherency. Additionally, the Channel-wise Texture Aggregation Memory (CaTeGory) infuses extrinsic knowledge, capitalizing on long-standing semantic textures. Our method also innovates the blurring diffusion process with the ResShift mechanism, finely balancing between sharpness and diffusion effects. Comprehensive experiments confirm our framework's advantage over state-of-the-art diffusion-based VSR techniques. The code is available: https://github.com/Tang1705/SeeClear-NeurIPS24.