Holographic-type communication (HTC) is on the verge of revolutionizing current communication paradigms. It will seamlessly connect people from distant locations through a fully immersive experience that will engage all five senses: sight, hearing, touch, smell, and taste. However, the practical realization and widespread adoption of HTC impose significant demands on current networks and end-user devices. While recent studies have primarily focused on discussing the HTC challenges and potential research directions, this paper takes a further step by evaluating the capabilities of wireless networks to meet HTC requirements. Specifically, it highlights the limitations of the fifth-generation (5G) networks by identifying HTC-related Key Performance Indicators (KPIs) and explores the potential of the sixth-generation (6G) networks. Moreover, it not only proposes potential research approaches for HTC enhancement but also analyzes their impact on the challenges in HTC implementation. Finally, the paper questions the ubiquitous potential of 6G, suggesting that a coordinated approach leveraging artificial intelligence (AI) for jointly optimizing user sites and communication networks is the most promising strategy, rather than solely relying on the capabilities of specific network generations.

This systematic review investigates compression algorithms for three-dimensional content, focusing on recent advancements. It categorizes the methodologies into traditional, learning-based, and semantic approaches. The review includes 52 studies selected based on criteria including publication date, peer reviewstatus, and relevance to the field. The analysis highlights the significant contributions of learning-based and semantic techniques in advancing 3D content compression. Notably, some reviewed learning-based methods demonstrated over 95% improvement in rate optimization compared to standard point cloud compression methods. Despite the comprehensive coverage, the review acknowledges certain limitations due to potential biases in study selection and the inherent heterogeneity of the included research. The findings underscore the importance of continued exploration in learning-based and semantic compression for enhancing the efficiency and applicability of 3D content technologies.

In the field of holographic-type communication (HTC), this paper presents a comprehensive exploration of existing technologies and proposes a novel, modular architecture for holographic telepresence systems (HTPSs). We substantiate our architectural framework through a practical implementation, demonstrating its modularity, interoperability, and versatility. Quantitative and qualitative assessments reveal both the promise and areas for improvement within our platform. Our findings reinforce the premise that the key to unlocking HTC’s future lies in modularity and interoperability, serving as critical pillars for efficient standardization and the development of minimal viable products.

Texture recognition is a fundamental task in computer vision, with diverse applications in material sciences, medicine, and agriculture. The ability to analyze complex patterns in images has been greatly enhanced by advancements in Deep Neural Networks and Vision Transformers. To address the challenging nature of texture recognition, this paper investigates the performance of several pre-trained vision architectures for texture recognition, including both CNN- and transformer-based models. For each architecture, multi-level features are extracted from early, intermediate, and final layers, concatenated, and fed into a trainable Multi-Layer Perceptron (MLP) classifier. The architecture is thoroughly evaluated using five publicly available texture datasets, KTH-TIPS2-b, FMD, GTOS-Mobile, DTD, and Soil, with MLP hyperparameters determined through an exhaustive grid search on one of the datasets to ensure optimal performance. Extensive experiments highlight the comparative performance of each architecture and demonstrate that aggregating features from different hierarchical levels improves texture recognition in most cases, outperforming even architectures that require substantially higher computational resources. The study also shows the particular effectiveness of transformer-based models, such as BEiTv2, in achieving state-of-the-art results on four of the five examined datasets.

Understanding surface textures through visual cues is crucial for applications in haptic rendering and virtual reality. However, accurately translating visual information into tactile feedback remains a challenging problem. To address this challenge, this paper presents a class-conditional Generative Adversarial Network (cGAN) for cross-modal translation from texture images to vibrotactile spectrograms, using samples from the LMT-108 dataset. The generator is adapted from pix2pix and enhanced with Conditional Batch Normalization (CBN) at the bottleneck to incorporate texture class semantics. A dedicated label predictor, based on a DenseNet-201 and trained separately prior to cGAN training, provides the conditioning label. The discriminator is derived from pix2pixHD and uses a multi-scale architecture with three discriminators, each comprising three downsampling layers. A grid search over multi-scale discriminator configurations shows that this setup yields optimal perceptual similarity measured by Learned Perceptual Image Patch Similarity (LPIPS). The generator is trained using a hybrid loss that combines adversarial, $L_1$, and feature matching losses derived from intermediate discriminator features, while the discriminators are trained using standard adversarial loss. Quantitative evaluation with LPIPS and Fréchet Inception Distance (FID) confirms superior similarity to real spectrograms. GradCAM visualizations highlight the benefit of class conditioning. The proposed model outperforms pix2pix, pix2pixHD, Residue-Fusion GAN, and several ablated versions. The generated spectrograms can be converted into vibrotactile signals using the Griffin–Lim algorithm, enabling applications in haptic feedback and virtual material simulation.

Efficient compression of sparse point cloud geometry remains a critical challenge in 3D content processing, particularly for low-rate scenarios where conventional codecs struggle to maintain efficiency. This work proposes a system-level framework for low-rate sparse geometry coding, leveraging three variants of autoencoder-based deep learning architectures: folding-based, graph convolution-based, and transformer-based. The proposed framework operates at the object level and utilizes semantic segmentation to structure scenes into interpretable intermediate representations. Two novel autoencoder architectures—a Graph Autoencoder and a Transformer Graph Autoencoder—are proposed and evaluated alongside a FoldingNet baseline. These models are benchmarked on both synthetic and real-world datasets and compared against standard codecs (G-PCC and Draco) as well as a state-of-the-art learning-based codec (CRCIR). Experimental results indicate that the proposed architectures consistently outperform both traditional and recent learning-based methods, particularly at low bitrates. High robustness to latent noise is also observed, enabling applicability in various transmission scenarios. The proposed Transformer Graph Autoencoder architecture achieves the best overall rate-distortion performance and exhibits strong generalization to unseen data.