Light field (LF) cameras, which can record real-word scenes from multiple viewpoints in a single shot, are widely used in 3D reconstruction, re-focusing, and virtual reality etc. However, the inherent trade-off between spatial resolution and angular resolution of LF images hinders their applications for scenarios requiring high resolutions. In this paper, we propose a novel intra-inter view interaction network for LF image super-resolution, termed as LF-IINet, to exploit the correlations among all views and simultaneously preserve the parallax structure of LF views. The proposed LF-IINet consists of two parallel branches. Specifically, the top branch extracts global inter-view information, and the bottom branch first independently maps each view to deep representations and then models the correlations among all intra-view features via proposed multi-view context block (MCB). The two branches interact with each other by proposed inter-assist-intra feature updating module (IntraFUM, where the intra feature are updated with the assistance of the inter feature) and intra-assist-inter feature updating module (InterFUM, where the inter feature are updated with the assistance of the intra feature). In this way, our LF-IINet incorporates rich angular and spatial information for LF image super-resolution. Extensive comparison with state-of-the-art methods demonstrates that our method achieves superior performance visually and quantitatively with reasonable parameters and FLOPs. Furthermore, quantitative results also show that our method is effective for LF images with both small and large disparities.

The acquisition of densely-sampled light field (LF) images is costly, which hampers the applications of LF imaging technology in 3D reconstruction, digital refocusing, virtual reality, etc . To mitigate the obstacle, various approaches have been proposed to reconstruct densely-sampled LF images from sparsely-sampled ones. However, most existing methods still suffer from the non-Lambertian effect and large disparity issue. In this paper, we embrace the challenges by introducing a new paradigm for LF angular super-resolution (SR), which first explores the multi-scale spatial-angular correlations on the sparse sub-aperture images (SAIs) and then performs angular SR on macro-pixel features. In this way, we propose an efficient LF angular SR network, termed as EASR, with simple 3D (2D) CNNs and reshaping operations. The proposed EASR can extract effective feature representations on SAIs and can handle large disparities well by performing angular SR on macro-pixel features. Extensive comparisons with state-of-the-art methods demonstrate that our method achieves superior performance visually and quantitatively. Furthermore, our method achieves efficient angular SR by providing an excellent tradeoff between reconstruction performance and inference time. Our code is available at https://github.com/GaoshengLiu/LF-EASR

The disparity information reflects pixel-wise inter-view correlations among sub-aperture images (SAIs) of a light field (LF) image. Existing CNN-based methods for LF spatial super-resolution (SR) rarely utilize the disparities to incorporate the underlying inter-view correlations due to the lack of ground-truth disparity labels. In this paper, we incorporate a self-supervised training strategy to estimate disparity maps, and simultaneously propose a disparity-guided network for LF spatial SR ( i.e. , LF-DGNet), in which the estimated disparity maps are utilized to modulate the LF features. Specifically, we introduce a disparity-guided feature modulation (DGFM) module where the disparity maps are utilized to produce affine transformation parameters for each view-wise feature. We also propose a multi-view feature recalibration (MFR) module which consists of a triple attention (TA, i.e. , spatial, channel, and angular attention) to enhance the ability of feature representation and further explore the intra-and inter-view correlations. Experimental results on public LF datasets including large-disparity LF images demonstrate that our proposed method achieves state-of-the-art performance both in quantitative results and visual quality. Our codes are available at https://github.com/GaoshengLiu/LF-DGNet

Vessel detection technology based on marine remote sensing imagery is of great importance. However, it often faces challenges, such as small vessel targets, cloud occlusion, insufficient data volume, and severely imbalanced class distribution in datasets. These issues result in conventional models failing to meet the accuracy requirements for practical applications. In this paper, we first construct a novel remote sensing vessel image dataset that includes various complex scenarios and enhance the data volume and diversity through data augmentation techniques. Secondly, we address the class imbalance between foreground (small vessels) and background in remote sensing imagery from two perspectives: the sensitivity of IoU metrics to small object localization errors and the innovative design of a cost-sensitive loss function. Specifically, at the dataset level, we select vessel targets appearing in the original dataset as templates and randomly copy–paste several instances onto arbitrary positions. This enriches the diversity of target samples per image and mitigates the impact of data imbalance on the detection task. At the algorithm level, we introduce the Normalized Wasserstein Distance (NWD) to compute the similarity between bounding boxes. This enhances the importance of small target information during training and strengthens the model’s cost-sensitive learning capabilities. Ablation studies reveal that detection performance is optimal when the weight assigned to the NWD metric in the model’s loss function matches the overall proportion of small objects in the dataset. Comparative experiments show that the proposed NWD-YOLO achieves Precision, Recall, and ${\mathrm{AP}}_{50}$ scores of 0.967, 0.958, and 0.971, respectively, meeting the accuracy requirements of real-world applications.

The dense light field sampling of focused plenoptic images (FPIs) yields substantial amounts of redundant data, necessitating efficient compression in practical applications. However, the presence of discontinuous structures and long-distance properties in FPIs poses a challenge. In this paper, we propose a novel end-to-end approach for learned focused plenoptic image compression (LFPIC). Specifically, we introduce a local-global correlation learning strategy to build the nonlinear transforms. This strategy can effectively handle the discontinuous structures and leverage long-distance correlations in FPI for high compression efficiency. Additionally, we propose a spatial-wise context model tailored for LFPIC to help emphasize the most related symbols during coding and further enhance the rate-distortion performance. Experimental results demonstrate the effectiveness of our proposed method, achieving a 22.16% BD-rate reduction (measured in PSNR) on the public dataset compared to the recent state-of-the-art LFPIC method. This improvement holds significant promise for benefiting the applications of focused plenoptic cameras. The code and pre-trained models are available at https://github.com/GaoshengLiu/LFPIC.