Cloud cover in multispectral imagery (MSI) poses significant challenges for early season crop mapping, as it leads to missing or corrupted spectral information. Synthetic aperture radar (SAR) data, which is not affected by cloud interference, offers a complementary solution, but lack sufficient spectral detail for precise crop mapping. To address this, we propose a novel framework, Time-series MSI Image Reconstruction using Vision Transformer (ViT), to reconstruct MSI data in cloud-covered regions by leveraging the temporal coherence of MSI and the complementary information from SAR from the attention mechanism. Comprehensive experiments, using rigorous reconstruction evaluation metrics, demonstrate that Time-series ViT framework significantly outperforms baselines that use non-time-series MSI and SAR or time-series MSI without SAR, effectively enhancing MSI image reconstruction in cloud-covered regions.
Summary: Errors in gradient trajectories introduce significant artifacts and distortions in magnetic resonance images, particularly in non-Cartesian imaging sequences, where imperfect gradient waveforms can greatly reduce image quality. Purpose: Our objective is to develop a general, nonlinear gradient system model that can accurately predict gradient distortions using convolutional networks. Methods: A set of training gradient waveforms were measured on a small animal imaging system, and used to train a temporal convolutional network to predict the gradient waveforms produced by the imaging system. Results: The trained network was able to accurately predict nonlinear distortions produced by the gradient system. Network prediction of gradient waveforms was incorporated into the image reconstruction pipeline and provided improvements in image quality and diffusion parameter mapping compared to both the nominal gradient waveform and the gradient impulse response function. Conclusion: Temporal convolutional networks can more accurately model gradient system behavior than existing linear methods and may be used to retrospectively correct gradient errors.
The exponential growth of IoT devices presents critical challenges in bandwidth-constrained wireless networks, particularly regarding efficient data transmission and privacy preservation. This paper presents a novel federated semantic communication (SC) framework that enables collaborative training of bandwidth-efficient models for image reconstruction across heterogeneous IoT devices. By leveraging SC principles to transmit only semantic features, our approach dramatically reduces communication overhead while preserving reconstruction quality. We address the fundamental challenge of client selection in federated learning environments where devices exhibit significant disparities in dataset sizes and data distributions. Our framework implements three distinct client selection strategies that explore different trade-offs between system performance and fairness in resource allocation. The system employs an end-to-end SC architecture with semantic bottlenecks, coupled with a loss-based aggregation mechanism that naturally adapts to client heterogeneity. Experimental evaluation on image data demonstrates that while Utilitarian selection achieves the highest reconstruction quality, Proportional Fairness maintains competitive performance while significantly reducing participation inequality and improving computational efficiency. These results establish that federated SC can successfully balance reconstruction quality, resource efficiency, and fairness in heterogeneous IoT deployments, paving the way for sustainable and privacy-preserving edge intelligence applications.
Deep neural networks have been shown to achieve exceptional performance for computer vision tasks like image recognition, segmentation, and reconstruction or denoising. Here, we evaluate the ultimate performance limits of deep convolutional neural network models for image reconstruction, by comparing them against the standard quantum limit set by shot-noise and the Heisenberg limit on precision. We train U-Net models on images of natural objects illuminated with coherent states of light, and find that the average mean-squared error of the reconstructions can surpass the standard quantum limit, and in some cases reaches the Heisenberg limit. Further, we train models on well-parameterized images for which we can calculate the quantum Cram\'er-Rao bound to determine the minimum possible measurable variance of an estimated parameter for a given probe state. We find the mean-squared error of the model predictions reaches these bounds calculated for the parameters, across a variety of parameterized images. These results suggest that deep convolutional neural networks can learn to become the optimal estimators allowed by the laws of physics, performing parameter estimation and image reconstruction at the ultimate possible limits of precision for the case of classical illumination of the object.
Reconstructing an animatable 3D human from casually captured images of an articulated subject without camera or human pose information is a practical yet challenging task due to view misalignment, occlusions, and the absence of structural priors. While optimization-based methods can produce high-fidelity results from monocular or multi-view videos, they require accurate pose estimation and slow iterative optimization, limiting scalability in unconstrained scenarios. Recent feed-forward approaches enable efficient single-image reconstruction but struggle to effectively leverage multiple input images to reduce ambiguity and improve reconstruction accuracy. To address these challenges, we propose PF-LHM, a large human reconstruction model that generates high-quality 3D avatars in seconds from one or multiple casually captured pose-free images. Our approach introduces an efficient Encoder-Decoder Point-Image Transformer architecture, which fuses hierarchical geometric point features and multi-view image features through multimodal attention. The fused features are decoded to recover detailed geometry and appearance, represented using 3D Gaussian splats. Extensive experiments on both real and synthetic datasets demonstrate that our method unifies single- and multi-image 3D human reconstruction, achieving high-fidelity and animatable 3D human avatars without requiring camera and human pose annotations. Code and models will be released to the public.
Numerous sparse inverse synthetic aperture radar (ISAR) imaging methods based on unfolded neural networks have been developed for high-quality image reconstruction with sparse measurements. However, their training typically requires paired ISAR images and echoes, which are often difficult to obtain. Meanwhile, one property can be observed that for a certain sparse measurement configuration of ISAR, when a target is rotated around its center of mass, only the image of the target undergoes the corresponding rotation after ISAR imaging, while the grating lobes do not follow this rotation and are solely determined by the sparse-sampling pattern. This property is mathematically termed as the equivariant property. Taking advantage of this property, an unfolded neural network for sparse ISAR imaging with self-supervised learning, named SS-ISAR-Net is proposed. It effectively mitigates grating lobes caused by sparse radar echo, allowing high-quality training to be achieved using only sparse radar echo data. The superiority of the proposed SS-ISAR-Net, compared to existing methods, is verified through experiments with both synthetic and real-world measurement data.
Dynamic Photoacoustic Computed Tomography (PACT) is an important imaging technique for monitoring physiological processes, capable of providing high-contrast images of optical absorption at much greater depths than traditional optical imaging methods. However, practical instrumentation and geometric constraints limit the number of acoustic sensors available around the imaging target, leading to sparsity in sensor data. Traditional photoacoustic (PA) image reconstruction methods, when directly applied to sparse PA data, produce severe artifacts. Additionally, these traditional methods do not consider the inter-frame relationships in dynamic imaging. Temporal resolution is crucial for dynamic photoacoustic imaging, which is fundamentally limited by the low repetition rate (e.g., 20 Hz) and high cost of high-power laser technology. Recently, Implicit Neural Representation (INR) has emerged as a powerful deep learning tool for solving inverse problems with sparse data, by characterizing signal properties as continuous functions of their coordinates in an unsupervised manner. In this work, we propose an INR-based method to improve dynamic photoacoustic image reconstruction from sparse-views and enhance temporal resolution, using only spatiotemporal coordinates as input. Specifically, the proposed INR represents dynamic photoacoustic images as implicit functions and encodes them into a neural network. The weights of the network are learned solely from the acquired sparse sensor data, without the need for external training datasets or prior images. Benefiting from the strong implicit continuity regularization provided by INR, as well as explicit regularization for low-rank and sparsity, our proposed method outperforms traditional reconstruction methods under two different sparsity conditions, effectively suppressing artifacts and ensuring image quality.
Quantitative magnetic resonance imaging (qMRI) provides tissue-specific parameters vital for clinical diagnosis. Although simultaneous multi-parametric qMRI (MP-qMRI) technologies enhance imaging efficiency, robustly reconstructing qMRI from highly undersampled, high-dimensional measurements remains a significant challenge. This difficulty arises primarily because current reconstruction methods that rely solely on a single prior or physics-informed model to solve the highly ill-posed inverse problem, which often leads to suboptimal results. To overcome this limitation, we propose LoREIN, a novel unsupervised and dual-prior-integrated framework for accelerated 3D MP-qMRI reconstruction. Technically, LoREIN incorporates both low-rank prior and continuity prior via low-rank representation (LRR) and implicit neural representation (INR), respectively, to enhance reconstruction fidelity. The powerful continuous representation of INR enables the estimation of optimal spatial bases within the low-rank subspace, facilitating high-fidelity reconstruction of weighted images. Simultaneously, the predicted multi-contrast weighted images provide essential structural and quantitative guidance, further enhancing the reconstruction accuracy of quantitative parameter maps. Furthermore, our work introduces a zero-shot learning paradigm with broad potential in complex spatiotemporal and high-dimensional image reconstruction tasks, further advancing the field of medical imaging.
We release NSD-Imagery, a benchmark dataset of human fMRI activity paired with mental images, to complement the existing Natural Scenes Dataset (NSD), a large-scale dataset of fMRI activity paired with seen images that enabled unprecedented improvements in fMRI-to-image reconstruction efforts. Recent models trained on NSD have been evaluated only on seen image reconstruction. Using NSD-Imagery, it is possible to assess how well these models perform on mental image reconstruction. This is a challenging generalization requirement because mental images are encoded in human brain activity with relatively lower signal-to-noise and spatial resolution; however, generalization from seen to mental imagery is critical for real-world applications in medical domains and brain-computer interfaces, where the desired information is always internally generated. We provide benchmarks for a suite of recent NSD-trained open-source visual decoding models (MindEye1, MindEye2, Brain Diffuser, iCNN, Takagi et al.) on NSD-Imagery, and show that the performance of decoding methods on mental images is largely decoupled from performance on vision reconstruction. We further demonstrate that architectural choices significantly impact cross-decoding performance: models employing simple linear decoding architectures and multimodal feature decoding generalize better to mental imagery, while complex architectures tend to overfit visual training data. Our findings indicate that mental imagery datasets are critical for the development of practical applications, and establish NSD-Imagery as a useful resource for better aligning visual decoding methods with this goal.
Sparse-view computed tomography (CT) is a practical solution to reduce radiation dose, but the resulting ill-posed inverse problem poses significant challenges for accurate image reconstruction. Although deep learning and diffusion-based methods have shown promising results, they often lack physical interpretability or suffer from high computational costs due to iterative sampling starting from random noise. Recent advances in generative modeling, particularly Poisson Flow Generative Models (PFGM), enable high-fidelity image synthesis by modeling the full data distribution. In this work, we propose Residual Poisson Flow (ResPF) Generative Models for efficient and accurate sparse-view CT reconstruction. Based on PFGM++, ResPF integrates conditional guidance from sparse measurements and employs a hijacking strategy to significantly reduce sampling cost by skipping redundant initial steps. However, skipping early stages can degrade reconstruction quality and introduce unrealistic structures. To address this, we embed a data-consistency into each iteration, ensuring fidelity to sparse-view measurements. Yet, PFGM sampling relies on a fixed ordinary differential equation (ODE) trajectory induced by electrostatic fields, which can be disrupted by step-wise data consistency, resulting in unstable or degraded reconstructions. Inspired by ResNet, we introduce a residual fusion module to linearly combine generative outputs with data-consistent reconstructions, effectively preserving trajectory continuity. To the best of our knowledge, this is the first application of Poisson flow models to sparse-view CT. Extensive experiments on synthetic and clinical datasets demonstrate that ResPF achieves superior reconstruction quality, faster inference, and stronger robustness compared to state-of-the-art iterative, learning-based, and diffusion models.
Autoregressive models are often employed to learn distributions of image data by decomposing the $D$-dimensional density function into a product of one-dimensional conditional distributions. Each conditional depends on preceding variables (pixels, in the case of image data), making the order in which variables are processed fundamental to the model performance. In this paper, we study the problem of observing a small subset of image pixels (referred to as a pixel patch) to predict the unobserved parts of the image. As our prediction mechanism, we propose a generalized and computationally efficient version of the convolutional neural autoregressive distribution estimator (ConvNADE) model adapted for real-valued and color images. Moreover, we investigate the quality of image reconstruction when observing both random pixel patches and low-discrepancy pixel patches inspired by quasi-Monte Carlo theory. Experiments on benchmark datasets demonstrate that choosing the pixels akin to a low-discrepancy sequence reduces test loss and produces more realistic reconstructed images.
Computed tomography (CT) is a major medical imaging modality. Clinical CT scenarios, such as low-dose screening, sparse-view scanning, and metal implants, often lead to severe noise and artifacts in reconstructed images, requiring improved reconstruction techniques. The introduction of deep learning has significantly advanced CT image reconstruction. However, obtaining paired training data remains rather challenging due to patient motion and other constraints. Although deep learning methods can still perform well with approximately paired data, they inherently carry the risk of hallucination due to data inconsistencies and model instability. In this paper, we integrate the data fidelity with the state-of-the-art generative AI model, referred to as the Poisson flow generative model (PFGM) with a generalized version PFGM++, and propose a novel CT framework: Flow-Oriented Reconstruction Conditioning Engine (FORCE). In our experiments, the proposed method shows superior performance in various CT imaging tasks, outperforming existing unsupervised reconstruction approaches.
Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public sRGB datasets. For this reason, many approaches try to generate realistic RAW images using sensor information and sRGB images. This paper covers the second challenge on RAW Reconstruction from sRGB (Reverse ISP). We aim to recover RAW sensor images from smartphones given the corresponding sRGB images without metadata and, by doing this, ``reverse" the ISP transformation. Over 150 participants joined this NTIRE 2025 challenge and submitted efficient models. The proposed methods and benchmark establish the state-of-the-art for generating realistic RAW data.
Recent work has shown improved lesion detectability and flexibility to reconstruction hyperparameters (e.g. scanner geometry or dose level) when PET images are reconstructed by leveraging pre-trained diffusion models. Such methods train a diffusion model (without sinogram data) on high-quality, but still noisy, PET images. In this work, we propose a simple method for generating subject-specific PET images from a dataset of multi-subject PET-MR scans, synthesizing "pseudo-PET" images by transforming between different patients' anatomy using image registration. The images we synthesize retain information from the subject's MR scan, leading to higher resolution and the retention of anatomical features compared to the original set of PET images. With simulated and real [$^{18}$F]FDG datasets, we show that pre-training a personalized diffusion model with subject-specific "pseudo-PET" images improves reconstruction accuracy with low-count data. In particular, the method shows promise in combining information from a guidance MR scan without overly imposing anatomical features, demonstrating an improved trade-off between reconstructing PET-unique image features versus features present in both PET and MR. We believe this approach for generating and utilizing synthetic data has further applications to medical imaging tasks, particularly because patient-specific PET images can be generated without resorting to generative deep learning or large training datasets.
Prior Arbitrary-Scale Image Super-Resolution (ASISR) methods often experience a significant performance decline when the upsampling factor exceeds the range covered by the training data, introducing substantial blurring. To address this issue, we propose a unified model, Stroke-based Cyclic Amplifier (SbCA), for ultra-large upsampling tasks. The key of SbCA is the stroke vector amplifier, which decomposes the image into a series of strokes represented as vector graphics for magnification. Then, the detail completion module also restores missing details, ensuring high-fidelity image reconstruction. Our cyclic strategy achieves ultra-large upsampling by iteratively refining details with this unified SbCA model, trained only once for all, while keeping sub-scales within the training range. Our approach effectively addresses the distribution drift issue and eliminates artifacts, noise and blurring, producing high-quality, high-resolution super-resolved images. Experimental validations on both synthetic and real-world datasets demonstrate that our approach significantly outperforms existing methods in ultra-large upsampling tasks (e.g. $\times100$), delivering visual quality far superior to state-of-the-art techniques.
Supervised machine learning has enabled accurate pathology detection in brain MRI, but requires training data from diseased subjects that may not be readily available in some scenarios, for example, in the case of rare diseases. Reconstruction-based unsupervised anomaly detection, in particular using diffusion models, has gained popularity in the medical field as it allows for training on healthy images alone, eliminating the need for large disease-specific cohorts. These methods assume that a model trained on normal data cannot accurately represent or reconstruct anomalies. However, this assumption often fails with models failing to reconstruct healthy tissue or accurately reconstruct abnormal regions i.e., failing to remove anomalies. In this work, we introduce a novel conditional diffusion model framework for anomaly detection and healthy image reconstruction in brain MRI. Our weakly supervised approach integrates synthetically generated pseudo-pathology images into the modeling process to better guide the reconstruction of healthy images. To generate these pseudo-pathologies, we apply fluid-driven anomaly randomization to augment real pathology segmentation maps from an auxiliary dataset, ensuring that the synthetic anomalies are both realistic and anatomically coherent. We evaluate our model's ability to detect pathology, using both synthetic anomaly datasets and real pathology from the ATLAS dataset. In our extensive experiments, our model: (i) consistently outperforms variational autoencoders, and conditional and unconditional latent diffusion; and (ii) surpasses on most datasets, the performance of supervised inpainting methods with access to paired diseased/healthy images.
Autoregressive visual generation has garnered increasing attention due to its scalability and compatibility with other modalities compared with diffusion models. Most existing methods construct visual sequences as spatial patches for autoregressive generation. However, image patches are inherently parallel, contradicting the causal nature of autoregressive modeling. To address this, we propose a Spectral AutoRegressive (SpectralAR) visual generation framework, which realizes causality for visual sequences from the spectral perspective. Specifically, we first transform an image into ordered spectral tokens with Nested Spectral Tokenization, representing lower to higher frequency components. We then perform autoregressive generation in a coarse-to-fine manner with the sequences of spectral tokens. By considering different levels of detail in images, our SpectralAR achieves both sequence causality and token efficiency without bells and whistles. We conduct extensive experiments on ImageNet-1K for image reconstruction and autoregressive generation, and SpectralAR achieves 3.02 gFID with only 64 tokens and 310M parameters. Project page: https://huang-yh.github.io/spectralar/.
Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation quality. This paper introduces VIVAT, a systematic approach to mitigating common artifacts in KL-VAE training without requiring radical architectural changes. We present a detailed taxonomy of five prevalent artifacts - color shift, grid patterns, blur, corner and droplet artifacts - and analyze their root causes. Through straightforward modifications, including adjustments to loss weights, padding strategies, and the integration of Spatially Conditional Normalization, we demonstrate significant improvements in VAE performance. Our method achieves state-of-the-art results in image reconstruction metrics (PSNR and SSIM) across multiple benchmarks and enhances text-to-image generation quality, as evidenced by superior CLIP scores. By preserving the simplicity of the KL-VAE framework while addressing its practical challenges, VIVAT offers actionable insights for researchers and practitioners aiming to optimize VAE training.
Vision encoders are increasingly used in modern applications, from vision-only models to multimodal systems such as vision-language models. Despite their remarkable success, it remains unclear how these architectures represent features internally. Here, we propose a novel approach for interpreting vision features via image reconstruction. We compare two related model families, SigLIP and SigLIP2, which differ only in their training objective, and show that encoders pre-trained on image-based tasks retain significantly more image information than those trained on non-image tasks such as contrastive learning. We further apply our method to a range of vision encoders, ranking them by the informativeness of their feature representations. Finally, we demonstrate that manipulating the feature space yields predictable changes in reconstructed images, revealing that orthogonal rotations (rather than spatial transformations) control color encoding. Our approach can be applied to any vision encoder, shedding light on the inner structure of its feature space. The code and model weights to reproduce the experiments are available in GitHub.
Prior methodologies have disregarded the diversities among distinct degradation types during image reconstruction, employing a uniform network model to handle multiple deteriorations. Nevertheless, we discover that prevalent degradation modalities, including sampling, blurring, and noise, can be roughly categorized into two classes. We classify the first class as spatial-agnostic dominant degradations, less affected by regional changes in image space, such as downsampling and noise degradation. The second class degradation type is intimately associated with the spatial position of the image, such as blurring, and we identify them as spatial-specific dominant degradations. We introduce a dynamic filter network integrating global and local branches to address these two degradation types. This network can greatly alleviate the practical degradation problem. Specifically, the global dynamic filtering layer can perceive the spatial-agnostic dominant degradation in different images by applying weights generated by the attention mechanism to multiple parallel standard convolution kernels, enhancing the network's representation ability. Meanwhile, the local dynamic filtering layer converts feature maps of the image into a spatially specific dynamic filtering operator, which performs spatially specific convolution operations on the image features to handle spatial-specific dominant degradations. By effectively integrating both global and local dynamic filtering operators, our proposed method outperforms state-of-the-art blind super-resolution algorithms in both synthetic and real image datasets.