Author name cluster

Weijie Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

EAAI Journal 2025 Journal Article

A review of speaker verification: Methods, network architectures, tasks and challenges

Weijie Wang
Hong Zhao
Yikun Yang
Yongjuan Yang

Speaker verification is an important branch of biometric recognition, with wide applications in identity authentication, audio monitoring, and other fields. In recent years, deep learning and meta-learning have made remarkable advancements in the field of speaker verification. Therefore, it is necessary to update existing reviews of speaker verification to reflect the latest research developments. We review literature from the past decade to provide a timely and comprehensive survey of the field. First, we outline the concept and system process of speaker verification. Then, we analyze the speech preprocessing process and common acoustic features used in the systems. Next, we present an overview of speaker modeling approaches, covering traditional probabilistic methods, deep learning-based speaker methods, and meta-learning-based speaker methods, focusing on the latter two methods. We provide an in-depth analysis and summary of the characteristics and the latest network architectures of these methods, focusing on the development of Transformer and large-scale pre-trained Transformer. Furthermore, we introduce the datasets and evaluation metrics used in speaker verification systems, focusing on a detailed and fair comparison of the performance of text-dependent and text-independent speaker verification systems. Finally, we explore the challenges faced by speaker verification systems and discuss future research opportunities.

Details DOI

ICRA Conference 2025 Conference Paper

TransDiff: Diffusion-Based Method for Manipulating Transparent Objects Using a Single RGB-D Image

Haoxiao Wang
Kaichen Zhou
Binrui Gu
Zhiyuan Feng
Weijie Wang
Peilin Sun
Yicheng Xiao
Jianhua Zhang

Manipulating transparent objects presents significant challenges due to the complexities introduced by their reflection and refraction properties, which considerably hinder the accurate estimation of their 3D shapes. To address these challenges, we propose a single-view RGB-D-based depth completion framework, TransDiff, that leverages the Denoising Diffusion Probabilistic Models(DDPM) to achieve material-agnostic object grasping in desktop. Specifically, we leverage features extracted from RGB images, including semantic segmentation, edge maps, and normal maps, to condition the depth map generation process. Our method learns an iterative denoising process that transforms a random depth distribution into a depth map, guided by initially refined depth information, ensuring more accurate depth estimation in scenarios involving transparent objects. Additionally, we propose a novel training method to better align the noisy depth and RGB image features, which are used as conditions to refine depth estimation step by step. Finally, we utilized an improved inference process to accelerate the denoising procedure. Through comprehensive experimental validation, we demonstrate that our method significantly outperforms the baselines in both synthetic and real-world benchmarks with acceptable inference time. The demo of our method can be found on: https://wang-haoxiao.github.io/TransDiff/

Details

NeurIPS Conference 2025 Conference Paper

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

Weijie Wang
Donny Y. Chen
Zeyu Zhang
Duochao Shi
Akide Liu
Bohan Zhuang

Feed-forward 3D Gaussian Splatting (3DGS) models have recently emerged as a promising solution for novel view synthesis, enabling one-pass inference without the need for per-scene 3DGS optimization. However, their scalability is fundamentally constrained by the limited capacity of their encoders, leading to degraded performance or excessive memory consumption as the number of input views increases. In this work, we analyze feed-forward 3DGS frameworks through the lens of the Information Bottleneck principle and introduce ZPressor, a lightweight architecture-agnostic module that enables efficient compression of multi-view inputs into a compact latent state $Z$ that retains essential scene information while discarding redundancy. Concretely, ZPressor enables existing feed-forward 3DGS models to scale to over 100 input views at 480P resolution on an 80GB GPU, by partitioning the views into anchor and support sets and using cross attention to compress the information from the support views into anchor views, forming the compressed latent state $Z$. We show that integrating ZPressor into several state-of-the-art feed-forward 3DGS models consistently improves performance under moderate input views and enhances robustness under dense view settings on two large-scale benchmarks DL3DV-10K and RealEstate10K.

PDF Details