Related papers: End-to-End Latency Optimization of Multi-view 3D R…

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe…

Neural Architecture Search (NAS) has enabled automatic discovery of more efficient neural network architectures, especially for mobile and embedded vision applications. Although recent research has proposed ways of quickly estimating…

In the rapidly evolving field of 3D reconstruction, 3D Gaussian Splatting (3DGS) and 2D Gaussian Splatting (2DGS) represent significant advancements. Although 2DGS compresses 3D Gaussian primitives into 2D Gaussian surfels to effectively…

Omnidirectional applications are immersive and highly interactive, which can improve the efficiency of remote collaborative work among factory workers. The transmission of omnidirectional video (OV) is the most important step in…

Pipeline parallelism is widely used to train large language models (LLMs). However, increasing heterogeneity in model architectures exacerbates pipeline bubbles, thereby reducing training efficiency. Existing approaches overlook the…

Using neural networks to represent 3D objects has become popular. However, many previous works employ neural networks with fixed architecture and size to represent different 3D objects, which lead to excessive network parameters for simple…

Multi-View Photometric Stereo (MVPS) is a popular method for fine-detailed 3D acquisition of an object from images. Despite its outstanding results on diverse material objects, a typical MVPS experimental setup requires a well-calibrated…

Unmanned Aerial Vehicles (UAVs) have emerged as a critical component in next-generation wireless networks, particularly for disaster recovery scenarios, due to their flexibility, mobility, and rapid deployment capabilities. This paper…

Light detection and ranging (Lidar) single-photon devices capture range and intensity information from a 3D scene. This modality enables long range 3D reconstruction with high range precision and low laser power. A multispectral…

Deep learning has made significant impacts on multi-view stereo systems. State-of-the-art approaches typically involve building a cost volume, followed by multiple 3D convolution operations to recover the input image's pixel-wise depth.…

Efficient video processing is a critical component in many IoMT applications to detect events of interest. Presently, many window optimization techniques have been proposed in event processing with an underlying assumption that the incoming…

We present 3DGS-LM, a new method that accelerates the reconstruction of 3D Gaussian Splatting (3DGS) by replacing its ADAM optimizer with a tailored Levenberg-Marquardt (LM). Existing methods reduce the optimization time by decreasing the…

In Unmanned Aerial Vehicle (UAV)-enabled mobile edge computing (MEC) systems, UAVs can carry edge servers to help ground user equipment (UEs) offloading their computing tasks to the UAVs for execution. This paper aims to minimize the total…

In this paper, we study the low-complexity channel reconstruction methods for downlink precoding in massive multiple-Input multiple-Output (MIMO) systems. When the user is allocated less streams than the number of its antennas, the base…

The ability to render scenes at adjustable fidelity from a single model, known as level of detail (LoD), is crucial for practical deployment of 3D Gaussian Splatting (3DGS). Existing discrete LoD methods expose only a limited set of…

Real-time, high-quality, 3D scanning of large-scale scenes is key to mixed reality and robotic applications. However, scalability brings challenges of drift in pose estimation, introducing significant errors in the accumulated model.…

This paper introduces the Masked Voxel Jigsaw and Reconstruction (MV-JAR) method for LiDAR-based self-supervised pre-training and a carefully designed data-efficient 3D object detection benchmark on the Waymo dataset. Inspired by the…

Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints.…

KV cache restoration has emerged as a dominant bottleneck in serving long-context LLM workloads, including multi-turn conversations, retrieval-augmented generation, and agentic pipelines. Existing approaches treat restoration as a…

Edge sensing and computing is rapidly becoming part of intelligent infrastructure architecture leading to operational reliance on such systems in disaster or emergency situations. In such scenarios there is a high chance of power supply…