Related papers: End-to-End Latency Optimization of Multi-view 3D R…
The structured nature of video data motivates introducing video-aware decisions that make use of this structure for improved video transmission over wireless networks. In this paper, we introduce an architecture for real-time video…
Mobile-edge computing (MEC) is expected to provide low-latency computation service for wireless devices (WDs). However, when WDs are located at cell edge or communication links between base stations (BSs) and WDs are blocked, the offloading…
3D Gaussian Splatting (3DGS) enables high-quality rendering of 3D scenes and is getting increasing adoption in domains like autonomous driving and embodied intelligence. However, 3DGS still faces major efficiency challenges when faced with…
In recent years, 3D hand pose estimation methods have garnered significant attention due to their extensive applications in human-computer interaction, virtual reality, and robotics. In contrast, there has been a notable gap in hand…
Device-to-device (D2D) communications is expected to be a critical enabler of distributed computing in edge networks at scale. A key challenge in providing this capability is the requirement for judicious management of the heterogeneous…
This paper introduces a parallel and asynchronous Transformer framework designed for efficient and accurate multilingual lip synchronization in real-time video conferencing systems. The proposed architecture integrates translation, speech…
The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant…
Cooperative inference in Mobile Edge Computing (MEC), achieved by deploying partitioned Deep Neural Network (DNN) models between resource-constrained user equipments (UEs) and edge servers (ESs), has emerged as a promising paradigm.…
3D Gaussian Splatting (3DGS) has gained significant attention for its high-quality rendering capabilities, ultra-fast training, and inference speeds. However, when we apply 3DGS to surface reconstruction tasks, especially in environments…
Recent advancements in 3D object reconstruction have been remarkable, yet most current 3D models rely heavily on existing 3D datasets. The scarcity of diverse 3D datasets results in limited generalization capabilities of 3D reconstruction…
Event cameras are bio-inspired sensors that output asynchronous and sparse event streams, instead of fixed frames. Benefiting from their distinct advantages, such as high dynamic range and high temporal resolution, event cameras have been…
Deep Neural Network (DNN) trained object detectors are widely deployed in many mission-critical systems for real time video analytics at the edge, such as autonomous driving and video surveillance. A common performance requirement in these…
3D object detection plays a pivotal role in many applications, most notably autonomous driving and robotics. These applications are commonly deployed on edge devices to promptly interact with the environment, and often require near…
Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase…
In this paper, we present a real-time approach to local trajectory replanning for microaerial vehicles (MAVs). Current trajectory generation methods for multicopters achieve high success rates in cluttered environments, but assume that the…
Video processing for real-time analytics in resource-constrained environments presents a significant challenge in balancing energy consumption and video semantics. This paper addresses the problem of energy-efficient video processing by…
3D Gaussian Splatting (3DGS) has emerged as a promising 3D reconstruction technique. The traditional 3DGS training pipeline follows three sequential steps: Gaussian densification, Gaussian projection, and color splatting. Despite its…
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-view ambiguities. Existing solutions typically suffer from poor…
3D reconstruction has lately attracted increasing attention due to its wide application in many areas, such as autonomous driving, robotics and virtual reality. As a dominant technique in artificial intelligence, deep learning has been…
3D reconstruction, which aims to recover the dense three-dimensional structure of a scene, is a cornerstone technology for numerous applications, including augmented/virtual reality, autonomous driving, and robotics. While traditional…