Co-authors
2
list available
Resume (English only)
Academic Achievements
- ArchGPT: Understanding the World's Architectures with Large Multimodal Models (arxiv 2025.09)
- Taking Language Embedded 3D Gaussian Splatting into the Wild (arxiv 2025.07)
- DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion (arxiv 2025.06)
- WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections (arxiv 2024.06)
- Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections (ACM MM 2025)
- RISE-Editing: Rotation-invariant Neural Point Fields with Interactive Segmentation for Fine-grained and Efficient Editing (Neural Networks 2025)
- Efficient interactive segmentation of three-dimensional Gaussians with optimal view selection (EAAI 2025)
- Look at the Sky: Sky-aware Efficient 3D Gaussian Splatting in the Wild (IEEE VR 2025 -- IEEE TVCG 2025, Best Paper Award)
- SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields (Pacific Graphics 2024 -- Computer Graphics Forum 2024)
- SG-NeRF: Semantic-guided Point-based Neural Radiance Fields (ICME, 2023)
- RIP-NeRF: Learning Rotation-Invariant Point-based Neural Radiance Field for Fine-grained Editing and Compositing (ICMR, 2023)
- An information entropy-based method of evidential source separation and refusion (IEEE Sensors Journal 2020)
- An improved multi-sensor D–S rule for conflict reassignment of failure rate of set (Soft Computing 2019)
Research Experience
- Main author or co-author in multiple research projects involving 3D content generation, human-computer interaction, and scene understanding.
Education
- Third-year 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.
Background
- Research interests: 3D content generation (reconstruction), human-computer interaction, and scene understanding for VR/MR/AR, especially using Internet-sourced data.
Miscellany
- Contact: Email / CV / Scholar / WeChat / Github