Advancements in 3D scene reconstruction have transformed 2D images from the real world into 3D models, producing realistic 3D results from hundreds of input photos. Despite great success in dense-view reconstruction scenarios, rendering a detailed scene from sparse views is still an ill-posed optimization problem, often resulting in artifacts and distortions in unseen areas. In this paper, we propose ReconX, a novel 3D scene reconstruction paradigm that reframes the ambiguous reconstruction problem as a temporal generation task. The key insight is to unleash the strong generative prior of large pre-trained video diffusion models for sparse-view reconstruction. Nevertheless, it is challenging to preserve 3D view consistency when directly generating video frames from pre-trained models. To address this issue, given limited input views, the proposed ReconX first constructs a global point cloud and encodes it into a contextual space as the 3D structure condition. Guided by the condition, the video diffusion model then synthesizes video frames that are detail-preserved and exhibit a high degree of 3D consistency, ensuring the coherence of the scene from various perspectives. Finally, we recover the 3D scene from the generated video through a confidence-aware 3D Gaussian Splatting optimization scheme. Extensive experiments on various real-world datasets show the superiority of ReconX over state-of-the-art methods in terms of quality and generalizability.

Triangle meshes play a crucial role in 3D applications for efficient manipulation and rendering. While auto-regressive methods generate structured meshes by predicting discrete vertex tokens, they are often constrained by limited face counts and mesh incompleteness. To address these challenges, we propose DeepMesh, a framework that optimizes mesh generation through two key innovations: (1) an efficient pre-training strategy incorporating a novel tokenization algorithm, along with improvements in data curation and processing, and (2) the introduction of Reinforcement Learning (RL) into 3D mesh generation to achieve human preference alignment via Direct Preference Optimization (DPO). We design a scoring standard that combines human evaluation with 3D metrics to collect preference pairs for DPO, ensuring both visual appeal and geometric accuracy. Conditioned on point clouds and images, DeepMesh generates meshes with intricate details and precise topology, outperforming state-of-the-art methods in both precision and quality. Project page: https://zhaorw02.github.io/DeepMesh/

Recently, the powerful text-to-image capabilities of GPT-4o have led to growing appreciation for native multimodal large language models. However, its multimodal capabilities remain confined to images and text. Yet beyond images, the ability to understand and generate 3D content is equally crucial. To address this gap, we propose ShapeLLM-Omni—a native 3D large language model capable of understanding and generating 3D assets and text in any sequence. First, we train a 3D vector-quantized variational autoencoder (VQVAE), which maps 3D objects into a discrete latent space to achieve efficient and accurate shape representation and reconstruction. Building upon the 3D-aware discrete tokens, we innovatively construct a large-scale continuous training dataset named 3D-Alpaca, encompassing generation, comprehension, and editing, thus providing rich resources for future research and training. Finally, we perform instruction-based fine-tuning of the Qwen-2.5-vl-7B-Instruct model on the 3D-Alpaca dataset, equipping it with native 3D understanding and generation capabilities. Our work represents an effective step toward extending multimodal large language models with fundamental 3D intelligence, paving the way for future advances in 3D-native AI.

The metaverse services are promising to embrace multi-sensory experiences of human beings, which mainly include audio-visual and tactile senses. From the perspective of wireless transmission, tactile transmission requires ultra-reliable low-latency communications, while audio-visual transmission requires enhanced mobile broadband communications. Besides, the audio-visual segment can be divided into several correlated data packets, any loss of packets would result in failed decoding at users, thus degrading users’ immersive experiences. In multi-user wireless metaverse systems, the heterogeneous transmission characteristics of multi-modal streams and integrity requirements of audio-visual stream transmission pose a great challenge to the limited wireless resource scheduling. To this end, we design a multi-user resource schedule scheme for multi-modal stream transmission by jointly considering the integrity of audio-visual stream transmission and the puncturing-based tactile stream transmission. We model the multi-modal perception utility function based on the multi-attribute utility theory and wireless transmission performance of multi-modal streams. Then, we formulate the average multi-modal perception utility maximization problem, and we adopt the Lyapunov theory to decompose the original maximization problem. Furthermore, we integrate the matching-based two-timescale spectrum resource allocation algorithm and alternating direction method of multipliers-based power allocation algorithm to obtain the optimal spectrum and power allocation strategies. Simulation results show that, compared with the resource allocation scheme without considering the transmission integrity, the average multi-modal perception utility of the proposed scheme is maximumly improved by 25%.

This paper investigates the spatio-temporal interference correlation in wireless networks, emphasizing the impact of spatial node rejection modeled by two types of Matern Hard-Core Point Processes (MHCP). We explore how the spatial rejection inherent to MHCP types I and II shapes interference patterns, with a particular focus on the negative correlation effects on network performance. Our study further examine the temporally correlated traffic model, which reveals significant insights into how temporal correlation affects interference. By deriving expressions for the interference correlation coefficient, we illustrate the critical role of path loss and spatial rejection parameters. The work contributes to a refined understanding of interference dynamics in networks modeled by MHCP and guides the strategic development of efficient wireless systems in the presence of correlated traffic.

To meet the imperative for sustainable low-carbon wireless communications, integrating distributed renewable energy sources with base stations is essential. However, there is often a mismatch between the energy generated by renewable sources and the energy required by base stations. To address this issue, optimization strategies such as traffic offloading and energy sharing are commonly employed. This paper introduces a spatial model based on stochastic geometry, mapping the spatial distribution of base stations and users, and quantifying the probability of coverage in cellular networks powered by renewable energy with energy-sharing and traffic offloading capabilities. Complementing this spatial analysis, we apply queuing theory to represent the base station energy status as a Markov chain, leading to a nuanced carbon emissions model post energy-sharing. Furthermore, a new metric called carbon efficiency is defined for accurately capturing the trade off between carbon emissions and performance of cellular networks. Simulations show that there is an optimal traffic offloading probability that can minimize carbon emissions in cellular networks while sacrificing the expected ergodic rate of users. These insights offer a foundation for developing optimization strategies that elevate the carbon efficiency of renewable-energy-driven cellular networks.

Beam tracking is a core issue in 5G vehicle-to-everything (V2X) networks. Specifically, higher beamforming gain is required to compensate for the path loss at higher frequencies, e.g., 5G FR2, to realize high data rate vehicle-toinfrastructure (V2I) communications. However, shorter time slots at higher frequencies, high velocity of vehicles, and unpredictable localization errors make this problem more challenging. Under these circumstances, wider beams can lead to higher beam tracking accuracy. Bear in mind that wider beams mean lower beamforming gain, which cannot compensate for high path loss at high frequencies and would further influence the data rate of V2I communications. Thus, there exists a trade-off between tracking accuracy and data rate in V2I communications. Furthermore, this problem needs to be solved within an extremely short time slot according to the high transmission frequency. To solve this problem, we propose a reinforcement learning (RL) assisted, high-resolution codebook-based beam tracking method. By comparing several different RL frameworks, we found that the twin delayed deep deterministic policy gradient (TD3) framework can help the roadside infrastructure (RSI) determine a proper beam pattern within a short duration. Moreover, according to the Hurst exponent analysis, recurrent neural networks (RNNs) are selected to improve the performance of the RL framework. The simulation results show that the proposed method performs well in tracking accuracy, data rate, and temporal efficiency.

With small cell networks becoming core parts of the fifth generation (5G) cellular networks, it is an important problem to evaluate the impact of user mobility on 5G small cell networks. However, the tendency and clustering habits in human activities have not been considered in traditional user mobility models. In this paper, human tendency and clustering behaviors are first considered to evaluate the user mobility performance for 5G small cell networks based on individual mobility model (IMM). As key contributions, user pause probability, user arrival, and departure probabilities are derived in this paper for evaluating the user mobility performance in a hotspot-type 5G small cell network. Furthermore, coverage probabilities of small cell and macro cell BSs are derived for all users in 5G small cell networks, respectively. Compared with the traditional random waypoint (RWP) model, IMM provides a different viewpoint to investigate the impact of human tendency and clustering behaviors on the performance of 5G small cell networks.

It is a great challenge to evaluate the network performance of cellular mobile communication systems. In this paper, we propose new spatial spectrum and energy efficiency models for Poisson-Voronoi tessellation (PVT) random cellular networks. To evaluate the user access to the network, a Markov chain based wireless channel access model is first proposed for PVT random cellular networks. On that basis, the outage probability and blocking probability of PVT random cellular networks are derived, which can be computed numerically. Furthermore, taking into account the call arrival rate, the path loss exponent and the base station (BS) density in random cellular networks, spatial spectrum and energy efficiency models are proposed and analyzed for PVT random cellular networks. Numerical simulations are conducted to evaluate the network spectrum and energy efficiency in PVT random cellular networks.

Compared with the conventional hexagonal cellular network structure, Poisson-Voronoi tessellated (PVT) random cellular network models can better capture the topology of real cellular networks. However, the random cellular network models are often complicated to analyze. To overcome this gap, in this paper we propose to analyze the performance of PVT random cellular networks using Markov chains. Using this technique, the blocking probability and the area spectral efficiency (ASE) models are obtained. Numerical results are demonstrated which show that our proposed techniques are effective approaches to evaluate the performance of random cellular networks.