arXiv subjects

Huai Qin

Publications and source records attributed to Huai Qin.

2 recordsLinked to original sources

arXiv2026

AI Empowered Communication and Radar Modulation Recognition: A Survey

Automatic modulation recognition (AMR) is of vital importance for ensuring communication and radar reliability, efficient spectrum utilization and resistance to electronic interference. The development of artificial intelligence (AI) technology is reshaping the technological paradigm of AMR, promoting its transition from traditional modes relying on manual features to data-driven intelligent recognition. This change is not only reflected in the significant improvement of recognition accuracy, but also injects strong momentum into the intelligent evolution of both communication and radar systems through algorithm innovation, architecture optimization, and scenario expansion. In order to clarify the current development status and bottlenecks of AMR, and to find breakthrough directions, we make a comprehensive survey of recent AI-based technologies for AMR in this paper, including model-based machine learning (ML) methods and data-driven deep learning (DL) methods. We first investigate the modulation types used in current communication and radar systems. Next, we summarize the typically used features in the field of AMR, and discuss their inherent advantages and disadvantages. Then, we introduce the basic AI models for AMR and conduct a hierarchical investigation of AMR methods for communication and radar. Finally, based on existing research works, we highlight open issues and propose future research directions for AMR.

eess.SP↗

arXiv2024

BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion

Witnessing the evolution of text-to-image diffusion models, significant strides have been made in text-to-3D generation. Currently, two primary paradigms dominate the field of text-to-3D: the feed-forward generation solutions, capable of swiftly producing 3D assets but often yielding coarse results, and the Score Distillation Sampling (SDS) based solutions, known for generating high-fidelity 3D assets albeit at a slower pace. The synergistic integration of these methods holds substantial promise for advancing 3D generation techniques. In this paper, we present BoostDream, a highly efficient plug-and-play 3D refining method designed to transform coarse 3D assets into high-quality. The BoostDream framework comprises three distinct processes: (1) We introduce 3D model distillation that fits differentiable representations from the 3D assets obtained through feed-forward generation. (2) A novel multi-view SDS loss is designed, which utilizes a multi-view aware 2D diffusion model to refine the 3D assets. (3) We propose to use prompt and multi-view consistent normal maps as guidance in refinement. Our extensive experiment is conducted on different differentiable 3D representations, revealing that BoostDream excels in generating high-quality 3D assets rapidly, overcoming the Janus problem compared to conventional SDS-based methods. This breakthrough signifies a substantial advancement in both the efficiency and quality of 3D generation processes.

cs.CV↗