Yuze Wang | 王宇泽

I'm a Ph.D. student under the supervision of Prof. Yue Qi at the State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University.

My research combines Computer Vision (CV), Computer Graphics (CG), and Extended Reality (XR) techniques to enable low-cost, interactive 3D scene generation from web-sourced multimodal data, with the long-term goal of powering immersive XR tourism experiences.

Feel free to contact me for any questions, collaboration opportunities, or just for a chat.

Yuze Wang profile image

Preprints

Manuscripts available on arXiv.

ArchGPT: Understanding the World's Architectures with Large Multimodal Models — overview

ArchGPT: Understanding the World's Architectures with Large Multimodal Models

Yuze Wang, Luo Yang, Junyi Wang, Yue Qi

arXiv, September 2025

WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections — overview

WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections

Yuze Wang, Junyi Wang, Yue Qi

arXiv, June 2024

Selected Publications

* denotes equal contribution or corresponding authorship, as indicated in the paper.

2026

TIP visual localization pipeline: GCFDNet descriptors and combined optimization of points, descriptors, and semantic objects

Visual Camera Localization by Globally Consistent Descriptor Learning and Combined Bundle Adjustment

Junyi Wang, Yuze Wang, Chen Wang, Yue Qi

IEEE Transactions on Image Processing (TIP) 2026

Urban-GS: A Unified 3D Gaussian Splatting Framework for Compact and High-Fidelity Aerial-to-Street Reconstruction — overview

Urban-GS: A Unified 3D Gaussian Splatting Framework for Compact and High-Fidelity Aerial-to-Street Reconstruction

Meng Wang, Changqun Xia, Yuze Wang, Junyi Wang, Wantong Duan, Xinxiong Xie, Yue Qi

IEEE/CVF CVPR 2026

GSBriefNet architecture for descriptor prediction, matching, and camera pose estimation

GSBrief: A Globally Consistent Descriptor with 3D Gaussian Splatting for Visual Localization

Junyi Wang, Yuze Wang, Wantong Duan, Meng Wang, Yue Qi

IEEE VR 2026

2025

3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion — overview

3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion

Junyi Wang, Yuze Wang, Wantong Duan, Meng Wang, Yue Qi

NeurIPS 2025

Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections — overview

Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections

Yongtang Bao, Chengjie Tang, Yuze Wang*, Haojie Li*

ACM Multimedia (MM) 2025

RISE-Editing: Rotation-invariant Neural Point Fields with Interactive Segmentation for Fine-grained and Efficient Editing — overview

RISE-Editing: Rotation-invariant Neural Point Fields with Interactive Segmentation for Fine-grained and Efficient Editing

Yuze Wang, Junyi Wang, Chen Wang, Yue Qi

Neural Networks 2025

Efficient interactive segmentation of three-dimensional Gaussians with optimal view selection — overview

Efficient interactive segmentation of three-dimensional Gaussians with optimal view selection

Yongtang Bao, Chengjie Tang, Yuze Wang*, Yutong Qi, Ruijun Liu*

Engineering Applications of Artificial Intelligence (EAAI) 2025

Look at the Sky: Sky-aware Efficient 3D Gaussian Splatting in the Wild — overview

Look at the Sky: Sky-aware Efficient 3D Gaussian Splatting in the Wild

Yuze Wang, Junyi Wang, Ruicheng Gao, Yansong Qu, Wantong Duan, Shuo Yang, Yue Qi

IEEE VR 2025 · IEEE Transactions on Visualization and Computer Graphics (TVCG)

IEEE VR 2025 Best Paper Award

2024

SCARF: Scalable Continual Learning Framework for Memory‐efficient Multiple Neural Radiance Fields — overview

SCARF: Scalable Continual Learning Framework for Memory‐efficient Multiple Neural Radiance Fields

Yuze Wang, Junyi Wang, Chen Wang, Wantong Duan, Yongtang Bao, Yue Qi

Pacific Graphics 2024 · Computer Graphics Forum (CGF)

2023

RIP-NeRF: Learning Rotation-Invariant Point-based Neural Radiance Field for Fine-grained Editing and Compositing — overview

RIP-NeRF: Learning Rotation-Invariant Point-based Neural Radiance Field for Fine-grained Editing and Compositing

Yuze Wang, Junyi Wang, Yansong Qu, Yue Qi

ACM ICMR 2023

2020

An improved multi-sensor D–S rule for conflict reassignment of failure rate of set — overview

An improved multi-sensor D–S rule for conflict reassignment of failure rate of set

Jiale Qiao, Jindong Zhang, Yuze Wang

Soft Computing 2020

An information entropy-based method of evidential source separation and refusion — overview

An information entropy-based method of evidential source separation and refusion

Yuze Wang, Jindong Zhang, Jiale Qiao

IEEE Sensors Journal 2020

Academic Services

Reviewer for IEEE TVCG, IEEE TMM, IEEE VR, CHI, IEEE ISMAR, PacificVis, CVPR, ECCV, ACM MM, etc.