To obtain a high coding gain, high‐efficiency video coding employs the recursive quad‐tree structured coding unit (CU) for the smallest coding layer. The computational complexity, however, increases dramatically because the CU and its associated prediction units (PUs) are tested thoroughly by the rate‐distortion (RD) optimisation method. To reduce the computational complexity, a fast CU decision algorithm is presented based on skipping of inter and intra PUs by checking the coded block flag (CBF) and RD cost. Experimental results show that the proposed algorithm saves ∼35.39% of encoding time.

Dense multi-view image reconstruction has been a focal point of research for an extended period, with recent surges in interest. The utilization of multi-view images offers solutions to numerous challenges and amplifies the effectiveness of various applications including 3D reconstruction, de-occlusion, depth sensing, saliency detection, and identifying salient objects. This paper introduces an approach to reconstructing high-density light field (LF) images, addressing the inherent challenge of balancing angular and spatial resolution caused by limited sensor resolution. We introduce an innovative approach to reconstructing LF images through a CNN-based network that combines spatial and epipolar features in both initial and deep feature extraction phases. Our network utilizes angular information during upsampling and employs dual feature extraction to effectively analyze horizontal and vertical epipolar data. Weight sharing within the CNN block between horizontal and vertically transposed stacks enhances quality while preserving model compactness. The outcomes of experiments carried out on real-world and synthetic datasets demonstrate the effectiveness of our method, showcasing its superior performance in both inference speed and reconstruction quality when compared to state-of-the-art (SOTA) techniques.

Recent research on dense multi-view image reconstruction has attracted considerable attention, due to its enhancement of applications such as 3D reconstruction, de-occlusion, depth sensing, saliency detection, and prominent object identification. This paper introduces a method for reconstructing high-density light field images, addressing the challenge of balancing angular and spatial resolution within the constraints of sensor resolution. We propose a three-stage network architecture for LF reconstruction that processes dense epipolar, spatial, and angular information efficiently. Our network processes epipolar information in the first stage, spatial information in the second stage, and angular information in the third stage. By extracting quadrilateral epipolar features from multiple directions, our model constructs a robust feature hierarchy for accurate reconstruction. We employ weight sharing in the initial stage to enhance feature quality while maintaining a compact model. Experimental results on real-world and synthetic datasets demonstrate that our approach surpasses state-of-the-art methods in both inference time and reconstruction quality.

Light field angular super-resolution (LFASR) aims to reconstruct densely sampled angular views from sparsely captured inputs, enabling high-fidelity rendering, refocusing, and depth estimation. In this paper, we propose a novel LFASR framework that employs a tri-visualization feature extraction strategy, which jointly processes Sub-Aperture Images (SAIs), Epipolar Plane Images (EPIs), and Macro-Pixel Images (MacroPIs) to comprehensively exploit the spatial-angular structure of light fields. These complementary representations are processed in parallel to extract diverse and informative features, which are then refined through a deep spatial aggregation module composed of residual blocks. The proposed pipeline consists of three key stages: Early Feature Extraction (EFE), Advanced Feature Refinement (AFR), and Angular Super-Resolution (ASR). Extensive experiments on both synthetic and real-world datasets demonstrate that our method achieves strong performance in terms of PSNR and SSIM, while maintaining strong generalization and robustness in challenging scenarios, including occlusions and large disparity variations. Moreover, qualitative evaluations confirm the method’s ability to preserve epipolar consistency and structural integrity across synthesized views, making it a reliable and efficient solution for practical LFASR applications.

We propose a self-supervised framework that combines an autoencoder and segmentation model to enhance anomaly detection and segmentation by inserting synthetic anomalies into the foreground regions of normal images. Synthetic anomalies were generated through a novel Patch Shuffle Superpixel Anomaly Insertion Method (PSSAIM), involving two stages. First, the normal images were divided into disjoint patches that were shuffled and rotated to produce distorted versions of the original images. Second, a Simple Linear Iterative Clustering (SLIC) superpixel extraction method is applied to distorted images to create abnormal segments that simulate real anomalies and cover a diverse range of synthetic anomalies. To identify regions of interest (RoI) where real defects typically occur,We developed a lightweight autoencoder (AE) model for each dataset class to identify RoIs where real defects typically occur. AE computes patch-wise similarities using the Structural Similarity Index Measure (SSIM) to map background areas, which are inverted to foreground regions using dissimilarity maps (1-SSIM). Threshold-based cleaning and region-based analysis refined the masks by removing noise and spurious blobs. For real test anomalies, we designed an enhanced segmentation model (EnSeg) featuring an encoder-decoder network with attention blocks and multiscale context aggregation. When trained on PSSAIM-augmented images, EnSeg achieved promising results: 98.9% area under the receiver operating characteristic curve (AUROC) for image-level detection, 77.1% average precision (AP) for pixel-level localization on the MVTec anomaly detection (MVTec AD) dataset, and 94.9% AUROC with 67.8% AP on the Kolektor SDD2 benchmark dataset. EnSeg also ensures rapid inference at 200 frames per second (fps), offering both accuracy and efficiency.