Search Results (42)

High dynamic range (HDR) imaging has received sustained interest for its ability to capture a wider scene radiance range than conventional imaging by fusing multi-exposure images. However, increasing the number of exposures aggravates ghosting artifacts during fusion, prompting modern devices to use only one or two shots. This leads to the fact that a single exposure is unable to simultaneously preserve details in both dark and bright regions, and even dual-exposure settings are insufficient to capture the full scene radiance. Under limited exposure conditions, distinct challenges arise for both physics-driven and data-driven models, with the former struggling to model unobserved irradiance distributions and the latter having difficulty capturing diverse exposure variations, leading to unrealistic brightness artifacts in highlights and shadows. To address this problem, we propose a mixed causal–acausal assisted compensation model that integrates physics-driven and data-driven modules to generate interpolated and extrapolated pseudo-exposure images for recovering missing brightness information. The proposed model decomposes pseudo-exposure image generation into a hybrid representation consisting of a causal part reflecting radiance variation and an acausal part capturing the residual scene structure. The causal representation is derived by estimating the physics-driven intensity mapping function from adjacent exposure images while the acausal one is obtained through a data-driven attention-augmented hybrid network. Both theoretical analysis and experimental results demonstrate that the pseudo-exposure images perform well in both objective and subjective evaluations. In addition, it is validated that incorporating interpolated or extrapolated images into raw images can indeed mitigate brightness artifacts in dual-exposure fusion as well as in single-exposure enhancement. Full article

The nonuniform raw data due to the varying pulse repetition interval (PRI) and the loss of echo pulses inevitably introduce azimuth grating lobes in the low-oversampled staggered synthetic aperture radar (LS-SAR) images, which result in ghost artifacts. In this paper, a deconvolution-based grating lobes reduction method for LS-SAR images is proposed to improve image quality. Firstly, the position-invariant property of azimuth grating lobes is theoretically analyzed and verified, and the LS-SAR image on the same range cell is mathematically modeled as the convolution between the scattering scene and the point spread function (PSF) of the LS-SAR imaging system, accompanied by the additive noise. Then, the PSF is numerically calculated according to the LS-SAR sampling strategy, the measured azimuthal antenna pattern, and the BP (Back Projection) imaging method. Finally, based on the Lucy–Richardson (LR) iterative deconvolution principle, the recovery of observed scenes and grating lobes reduction can be simultaneously achieved by deconvoluting the LS-SAR image with the acquired PSF. Both simulated experiments with point-array targets and real SAR images, as well as validation experiments with airborne measured LS-SAR data, demonstrated the effectiveness of the proposed method. Full article

The infrared (IR)—visible light (VIS) dual-camera system provides complementary cues for image fusion, but issues such as geometric mismatch caused by different imaging methods, inconsistent resolution/field-of-view, and installation offsets often lead to ghosting and artifacts. This study aims to develop a fast-deployable and repeatable calibration workflow based on cost-effective calibration board. We designed an infrared-visible high-contrast checkerboard plate that can be generated through structural parameterization and efficiently manufactured using Python/OpenSCAD. We also established a corner-based registration pipeline that estimates global homography to align the visible-light images onto the infrared pixel grid for fusion and quantitative evaluation. Experiments conducted in a controlled indoor environment demonstrated stable sub-pixel performance within a range of 1.5–2.5 m, with an average re-projection error of 0.47–0.50 pixels per frame and a 95th percentile lower than 0.51 pixels. The corner position re-projection error test further confirmed stability near image boundaries, with a median value of 0.53–0.63 pixels and a 95th percentile of 0.54–0.64 pixels. Overall, the proposed target design and workflow can achieve practical infrared-visible calibration under typical deployment constraints and have repeatable accuracy, providing geometrically consistent input for subsequent fusion and dataset construction. Full article

Unmanned Aerial Vehicle (UAV) orthophoto generation in complex environments remains challenging because weak textures, reflective surfaces, occlusions, and large scene extents can cause incomplete reconstruction, ghosting, and seam artifacts. Although 3D Gaussian Splatting (3DGS) offers an efficient explicit scene representation, its use in large-scale UAV orthophoto generation is limited by high memory consumption, unstable densification, and insufficient support for mapping-oriented orthographic rendering. This paper proposes a single-GPU 3DGS framework for UAV orthophoto generation by integrating adaptive spatial block partitioning, deterministic structure-sensitive adaptive density control, and core–buffer tiled orthographic rendering with weighted blending. The proposed framework decomposes large scenes into resource-bounded subregions, guides Gaussian densification using fixed multi-view neighborhoods and edge-enhanced dynamic consistency, and generates large-format orthophotos with reduced boundary and seam artifacts. Experiments on MatrixCity-S and multiple UAV photogrammetric datasets show that the method achieves competitive reconstruction quality and improved resource efficiency. On MatrixCity-S, it reaches 29.01 dB PSNR and 0.901 SSIM, while completing training in 1 h 49 min on a single NVIDIA RTX 3090 GPU. Compared with BlockGS, peak VRAM consumption is reduced by more than 38% across datasets. Under geo-aligned comparison conditions, line-measurement comparisons with MetaShape and Pix4DMapper yield RMSE values of 0.099 m and 0.087 m, respectively. These results demonstrate the potential of the proposed framework for memory-efficient 3DGS-based UAV orthophoto generation under constrained hardware resources, while further control-point-based validation is still needed for rigorous surveying-grade applications. Full article

The lateral organization of the plasma membrane (PM) is vital for cellular signaling, yet the specific mechanisms by which the internal cortical actin meshwork templates the organization of the external lipid leaflet remain poorly understood. While established models like the ‘picket-fence’ emphasize physical barriers to diffusion, recent observations of fiber-like “ghost” structures in the distribution of glycosylphosphatidylinositol-anchored proteins (GPI-APs) suggest a more intricate mode of spatial coordination. In this study, we utilize imaging total internal reflection fluorescence correlation spectroscopy (ITIR-FCS) and variable-angle TIRF to resolve whether these filamentous patterns represent genuine membrane-proximal features or optical artifacts of cytosolic transport. Our results demonstrate that these fiber-like tracks are strictly confined to the immediate PM interface and disappear as the evanescent field probes deeper into the cytosol. While the spatial distribution of GPI-APs is templated by the underlying actin meshwork, quantitative diffusion mapping shows that the lateral dynamics of the probe remains largely uniform and is not significantly modulated by these filamentous patterns. By pharmacologically perturbing the actin scaffold and membrane cholesterol, we show that this transbilayer coupling is contingent upon a cholesterol-dependent cytoskeletal pinning mechanism. These findings demonstrate a decoupling of spatial organization and molecular dynamics, providing evidence for how the actin scaffold patterns nanoscale membrane organization without imposing long-range barriers to diffusion. Full article

Synthetic aperture radar (SAR) ship detection is severely limited by the artifacts caused by motion. Due to the complex six-degree-of-freedom (6-DOF) motion of ships, the ship imaging exhibits aberration phenomena including spatial blurring, discrete ghosting, and Lorentz linear blurring. Traditional detectors rely on the identification of static spatial features. When the phase coherence is disrupted, they tend to fail. To overcome this problem, we propose a multimodal fusion framework based on physical principles. This framework establishes a theoretical connection between the ship hydrodynamic response and imaging degradation through short, long, and ultra-long coherence processing intervals (CPI). The framework adopts a cascaded architecture: first, a lightweight YOLOv8 performs rapid global screening, followed by a signal backtracking mechanism that extracts high-fidelity time-frequency domain (TFD) and range instantaneous Doppler (RID) features from the original distance compressed data. In the second-level detection, these physical features are adaptively fused with spatial intensity through a YOLOv8 network integrated with the convolutional block attention module (CBAM) to reduce the false detection rate. The validation on high-fidelity simulations and real GF-3 datasets shows that this method consistently achieves an average precision (mAP) of over 95%, outperforming several widely used detectors, and demonstrates strong generalization ability in extreme imaging conditions, suitable for maritime detection scenarios. Full article

With the widespread adoption of various types of Unmanned Aerial Vehicles (UAVs), their non-compliant operations pose a severe challenge to public safety, necessitating the urgent identification and detection of UAV targets. However, in complex backgrounds, UAV targets exhibit small-scale dimensions and low contrast, coupled with extremely low signal-to-noise ratios. This forces conventional target detection methods to confront issues such as feature convergence, missed detections, and false alarms. To address these challenges, we propose a Multi-View Feature Fusion Network (MVFF) that achieves precise identification of small, low-contrast UAV targets by leveraging complementary multi-view information. First, we design a collaborative view alignment fusion module. This module employs a cross-map feature fusion attention mechanism to establish pixel-level mapping relationships and perform deep fusion, effectively resolving geometric distortion and semantic overlap caused by imaging angle differences. Furthermore, we introduce a view feature smoothing module that employs displacement operators to construct a lightweight long-range modeling mechanism. This overcomes the limitations of traditional convolutional local receptive fields, effectively eliminating ghosting artifacts and response discontinuities arising from multi-view fusion. Additionally, we developed a small object binary cross-entropy loss function. By incorporating scale-adaptive gain factors and confidence-aware weights, this function enhances the learning capability of edge features in small objects, significantly reducing prediction uncertainty caused by background noise. Comparative experiments conducted on a multi-perspective UAV dataset demonstrate that our approach consistently outperforms existing state-of-the-art methods across multiple performance metrics. Specifically, it achieves a Structure-measure of 91.50% and an F-measure of 85.14%, validating the effectiveness and superiority of the proposed method. Full article

Infrared and visible image fusion is a critical technology for enhancing the all-weather perception capabilities of autonomous driving systems. However, the inherent physical parallax of vehicle-mounted sensors combined with motion-induced vibrations makes it difficult to achieve strict alignment between the source images. Direct fusion of such misaligned pairs leads to ghosting artifacts, which significantly compromises driving safety. To address this challenge, this paper proposes a cascaded deep fusion framework tailored for autonomous driving scenarios. A dual-modal perception dataset is first constructed, incorporating realistic physical parallax and non-rigid deformations. Subsequently, a decoupled strategy is established, characterized by geometric correction followed by semantic fusion: the Static-Feature Recursive Registration (SFRR) network is utilized to explicitly correct the spatial misalignments caused by parallax, thereby establishing geometric consistency; then, the Hierarchical Invertible Block Fusion (HIBF) network achieves lossless integration of cross-modal features by combining spatial frequency separation with invertible interaction techniques. Experimental results demonstrate that the proposed method outperforms representative algorithms across several metrics, including Mutual Information (MI), Visual Information Fidelity (VIF), Structural Similarity (SSIM), and Correlation Coefficient (CC), producing high-quality fused images with clear structural definitions. Full article

Conventional image stitching pipelines predominantly rely on homographic alignment, whose planar assumption often breaks down in dual-camera configurations capturing non-planar scenes, producing geometric warping, bulging, and structural distortion. To address these limitations, this paper presents SENA (Seamlessly Natural), a geometry-driven image stitching approach with three complementary contributions. First, we propose a hierarchical affine-based warping strategy that combines global affine initialization, local affine refinement, and a smooth free-form deformation field regulated by seamguard adaptive smoothing. This multi-scale design preserves local shape, parallelism, and aspect ratios, thereby reducing the hallucinated distortions commonly associated with homography-based models. Second, SENA incorporates a geometry-driven adequate zone detection mechanism that identifies regions with reduced parallax directly from the disparity consistency of correspondences filtered by RANSAC, without relying on semantic segmentation or depth estimation. Third, within this zone, anchor-based seamline cutting and segmentation enforce one-to-one geometric correspondence between image pairs, reducing ghosting and smearing artifacts. Extensive experiments demonstrate that SENA achieves 26.2 dB PSNR and 0.84 SSIM, obtains the lowest BRISQUE score (33.4) among compared methods, and reduces runtime by 79% on average across resolutions. These results confirm improved structural fidelity and computational efficiency while maintaining competitive alignment accuracy. Full article

Dynamic street-scene reconstruction from sparse viewpoints over long temporal spans is challenged by temporal instability, ghosting near occlusions, and background drift. This paper presents SPT-Gauss (Semantic Prior and Temporal constraint-enhanced Gaussian splatting), a Gaussian-splatting framework that improves dynamic reconstruction without object-level annotations by combining dense semantic priors with lightweight, parameter-level temporal regularization. SPT-Gauss distills per-pixel semantic features from a frozen 2D foundation model into 4D Gaussian primitives, estimates static and dynamic regions via a dual-evidence motion mask, and regularizes temporal parameters through a semantic-guided velocity constraint and a static-lifetime prior to suppress spurious background motion. Experiments on the Waymo Open Dataset and KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) show consistent improvements over representative baselines in both 4D reconstruction and novel-view synthesis, with reduced temporal artifacts and improved fidelity in motion-challenging regions. Full article

We report on the post-capture, on-demand deblurring technique based on a Dynamic Vision Sensor (DVS). Motion blur causes photographic defects inherently in most use cases of mobile cameras. To compensate for motion blur in mobile photography, we use a fast event-based vision sensor. However, in this paper, we found severe artifacts resulting in image quality degradation caused by color ghosts, event noises, and discrepancies between conventional image sensors and event-based sensors. To overcome these inevitable artifacts, we propose and demonstrate event-based compensation techniques such as cross-correlation optimization, contrast maximization, resolution mismatch compensation (event upsampling for alignment), and disparity matching. The results show that the deblur performance can be improved dramatically in terms of metrics such as the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Spatial Frequency Response (SFR). Thus, we expect that the proposed event-based image restoration technique can be widely deployed in mobile cameras. Full article

Brain magnetic resonance imaging (MRI) is highly susceptible to motion artifacts that degrade fine structural details and undermine quantitative analysis. Conventional U-Net-based deep learning approaches for motion artifact reduction typically operate only in the image domain and are often trained on data with simplified motion patterns, thereby limiting physical plausibility and generalization. We propose Sim-DDNet, a simulation-data-based dual-domain network that combines k-space-based motion simulation with a joint image-k-space reconstruction architecture. Motion-corrupted data were generated from T2-weighted Alzheimer’s Disease Neuroimaging Initiative brain MR scans using a k-space replacement scheme with three to five random rotational and translational events per volume, yielding 69,283 paired samples (49,852/6969/12,462 for training/validation/testing). Sim-DDNet integrates a real-valued U-Net-like image branch and a complex-valued k-space branch using cross attention, FiLM-based feature modulation, soft data consistency, and composite loss comprising L1, structural similarity index measure (SSIM), perceptual, and k-space-weighted terms. On the independent test set, Sim-DDNet achieved a peak signal-to-noise ratio of 31.05 dB, SSIM of 0.85, and gradient magnitude similarity deviation of 0.077, consistently outperforming U-Net and U-Net++ across all three metrics while producing less blurring, fewer residual ghost/streak artifacts, and reduced hallucination of non-existent structures. These results indicate that dual-domain, data-consistency-aware learning, which explicitly exploits k-space information, is a promising approach for physically plausible motion artifact correction in brain MRI. Full article

Recent text-to-image AI systems have revived the long-standing fantasy of the image that appears to generate itself. Building on Chesher and Albarrán-Torres’s concept of ‘autolography’, this article situates contemporary AI-generated imagery within a longer lineage of self-generating images that extends from religious acheiropoieta (‘not made by hand’) through photography to computational image-making. Through the lens of Practice-as-Research (PaR), it positions digital photogrammetry as a knowledge ground in which the fantasy of the self-generating image continues to perform the faith structures of earlier visual cultures. Drawing on photogrammetric experiments originating within Lisbon’s Church of São Domingos in 2018, this article examines unexpected artifacts—ghosts, smears, and fragmentations—that emerge from movement, and reveal the body of the researcher in the centre. It argues that such digital ‘miracle’ images function as contingent, embodied events, and renders visible the labour, presence, and gestures typically erased by automated systems. It playfully proposes the ‘cheiropoieton’ (‘made by hand’) as an embodied counter-ethics to autolography, insisting on friction, care, and accountability in contemporary image-making. Full article

In the wild, snow is not merely additive noise; it is a non-stationary, semi-transparent veil whose spatial statistics vary with depth, illumination, and wind. Because conventional two-stage pipelines first detect a binary mask and then inpaint the occluded regions, any early mis-classification is irreversibly baked into the final result, leading to over-smoothed textures or ghosting artifacts. We propose BAT-Net, a Bidirectional Attention Transformer Network that frames desnowing as a coupled representation learning problem, jointly disentangling snow appearance and scene radiance in a single forward pass. Our core contributions are as follows: (1) A novel dual-decoder architecture where a background decoder and a snow decoder are coupled via a Bidirectional Attention Module (BAM). The BAM implements a continuous predict–verify–correct mechanism, allowing the background branch to dynamically accept, reject, or refine the snow branch’s occlusion hypotheses, dramatically reducing error accumulation. (2) A lightweight yet effective multi-scale feature fusion scheme comprising a Scale Conversion Module (SCM) and a Feature Aggregation Module (FAM), enabling the model to handle the large scale variance among snowflakes without a prohibitive computational cost. (3) The introduction of the FallingSnow dataset, curated to eliminate the label noise caused by irremovable ground snow in existing benchmarks, providing a cleaner benchmark for evaluating dynamic snow removal. Extensive experiments on synthetic and real-world datasets demonstrate that BAT-Net sets a new state of the art. It achieves a PSNR of 35.78 dB on the CSD dataset, outperforming the best prior model by 1.37 dB, and also achieves top results on SRRS (32.13 dB) and Snow100K (34.62 dB) datasets. The proposed method has significant practical applications in autonomous driving and surveillance systems, where accurate snow removal is crucial for maintaining visual clarity. Full article

In order to improve image visual quality in high dynamic range (HDR) scenes while avoiding motion ghosting artifacts caused by exposure time differences, innovative image sensors captured two registered extreme-exposure-ratio (EER) image pairs with complementary and symmetric exposure configurations for high dynamic range imaging (HDRI). However, existing multi-exposure fusion (MEF) algorithms suffer from luminance inversion artifacts in overexposed and underexposed regions when directly combining such EER image pairs. This paper proposes a neural network-based framework for HDRI based on attention mechanisms and edge assistance to recover missing luminance information. The framework derives local luminance representations from a convolution kernel perspective, and subsequently refines the global luminance order in the fused image using a Transformer-based residual group. To support the two-stage process, multi-scale channel features are extracted from a double-attention mechanism, while edge cues are incorporated to enhance detail preservation in both highlight and shadow regions. The experimental results validate that the proposed framework can alleviate luminance inversion in HDRI when inputs are two EER images, and maintain fine structural details in complex HDR scenes. Full article