Three-Dimensional Gaussian Splatting (3DGS) has revolutionized novel-view synthesis, enabling real-time rendering of high-quality scenes. Two-Dimensional Gaussian Splatting (2DGS) improves geometric accuracy by replacing 3D Gaussians with flat 2D Gaussians. However, the flat nature of 2D Gaussians reduces mesh quality on volumetric surfaces and results in over-smoothed reconstruction. To address this, we propose Dual-Dimensional Gaussian Splatting (DDGS), which integrates both 2D and 3D Gaussians. First, we generalize the homogeneous transformation matrix based on 2DGS to initialize all Gaussians in 3D. Subsequently, during training, we selectively convert Gaussians into 2D representations based on their scale. This approach leverages the complementary strengths of 2D and 3D Gaussians, resulting in more accurate surface reconstruction across both flat and volumetric regions. Additionally, to mitigate over-smoothing, we introduce gradient-based regularization terms. Quantitative evaluations on the DTU and TnT datasets demonstrate that DDGS consistently outperforms prior methods, including 3DGS, SuGaR, and 2DGS, achieving the best Chamfer Distance and F1 score across a wide range of scenes.

Light field (LF) reconstruction is a technique for synthesizing views between LF images and various methods have been proposed to obtain high-quality LF reconstructed images. In this paper, we propose a progressive exploration network using efficient channel fusion for light field reconstruction (Prex-Net), which consists of three parts to quickly produce high-quality synthesized LF images. The initial feature extraction module uses 3D convolution to obtain deep correlations between multiple LF input images. In the channel fusion module, the extracted initial feature map passes through successive up- and down-fusion blocks and continuously searches for features required for LF reconstruction. The fusion block collects the pixels of channels by pixel shuffle and applies convolution to the collected pixels to fuse the information existing between channels. Finally, the LF restoration module synthesizes LF images with high angular resolution through simple convolution using the concatenated outputs of down-fusion blocks. The proposed Prex-Net synthesizes views between LF images faster than existing LF restoration methods and shows good results in the PSNR performance of the synthesized image.

Light field angular super-resolution (LFASR) aims to reconstruct densely sampled views from sparse inputs by exploiting spatial–angular correlations, thereby producing rich spatial–angular representations and enabling applications such as 3D reconstruction, refocusing, and virtual reality. In this paper, we propose a multi-receptive field spatial–angular (MRF-SA) framework that jointly captures fine-grained details and long-range dependencies through complementary spatial and angular branches. This design enables effective modeling of disparity-aware interactions without relying on computationally expensive attention mechanisms. In addition, we introduce a lightweight variant based on depth-wise separable convolutions to achieve a favorable tradeoff between reconstruction accuracy and computational efficiency. Extensive experiments on both real-world and synthetic datasets demonstrate that the proposed method achieves competitive performance compared to state-of-the-art approaches.

Light field angular super-resolution (LFASR) seeks to recover missing viewpoints from sparsely captured angular samples, while preserving the underlying scene structure across views. This task is complicated by disparity-induced variations, incomplete visibility near occlusion boundaries, and view-dependent appearance changes caused by reflective surfaces. In this work, we propose a Cross-Domain EPI–Spatial–Angular (X-ESA) framework that combines EPI-based geometric modeling with complementary spatial and angular feature extraction. A CSWin-based EPI transformer captures long-range, slope-aligned dependencies, while dedicated convolutional branches refine spatial details and cross-view relationships. These features are integrated through a mesh–progressive fusion strategy, followed by channel attention and spatial residual refinement. Extensive experiments on real-world and synthetic datasets demonstrate that the proposed method achieves competitive reconstruction performance compared with state-of-the-art LFASR approaches.

Compressed video bitstreams are intended for real-time transmission over communication networks. Because video coding standards eliminate the temporal, spatial, and statistical redundancies, the coded video bitstreams are very sensitive to transmission errors. Many error resilience coding schemes are available to get high video quality over noisy channels. We propose an error resilient coding technique to limit the effect of error propagation in low bit-rate video coding. The success of error resilient coding techniques relies on how accurately the transmission errors can be detected. Therefore, we propose a very simple error detection technique using data hiding. After error detection, we conceal the corrupted MB data using intra MB refresh and motion compensation with the estimated motion vector. This method will be useful in video communication in error prone environment such as WCDMA networks

Light field angular super-resolution (LFASR) seeks to recover missing viewpoints from sparsely captured angular samples, while preserving the underlying scene structure across views. This task is complicated by disparity-induced variations, incomplete visibility near occlusion boundaries, and view-dependent appearance changes caused by reflective surfaces. In this work, we propose a cross-domain EPI–spatial–angular (X-ESA) framework that combines EPI-based geometric modeling with complementary spatial and angular feature extraction. A CSWin-based EPI transformer captures long-range, slope-aligned dependencies, while dedicated convolutional branches refine spatial details and cross-view relationships. These features are integrated through a mesh–progressive fusion strategy, followed by channel attention and spatial residual refinement. Experiments on real-world and synthetic datasets under the $2\times 2\to 7\times 7$ setting result in average performances of $41.29$ dB/$0.989$ SSIM and $40.98$ dB/$0.989$ SSIM, respectively. The proposed model contains $2.84$ M trainable parameters and provides competitive reconstruction quality relative to existing LFASR methods.