About Me

I’m a Research Engineer affiliated with the USC Institute for Creative Technologies, and my research passion lies in the intersection of Computer Vision and Machine Learning.

Currently, my primary focus is on projects related to 3D vision, with a special emphasis on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting.

Education

Dalian University of Technology

September 2018 - June 2022

Bachelor of Engineering in Cyber Engineering

September 2018 - June 2022

GPA: 88/100

University of Southern California

August 2022 - May 2024

Master of Science in Computer Science (Honors)

August 2022 - May 2024

GPA: 4.0/4.0

Publication

AtomGS: Atomizing Gaussian Splatting for High-Fidelity Radiance Field

Rong Liu, Rui Xu, Yue Hu, Meida Chen, Andrew Feng

Pre-Print arXiv:2405.12369

Project Page | Paper | Code

Universal Photorealistic Style Transfer: A Lightweight and Adaptive Approach

Rong Liu, Enyu Zhao, Zhiyuan Liu, Andrew Feng, Scott John Easley

Pre-Print arXiv:2309.10011

Project Page | Paper | Code

UAV swarm based radar signal sorting via multi-source data fusion: A deep transfer learning framework

Liangtian Wan, Rong Liu, Lu Sun, Hansong Nie, Xianpeng Wang

Information Fusion. 78 (2022): 90-101

Paper | Patent

Project

Gaussian Splatting Monitor

We aim to extend 3D Gaussian Splatting, currently limited to RGB rendering and loss, by incorporating differentiable outputs inspired by the versatile Neural Radiance Fields (NeRF), thus enabling advanced research and novel loss functions for improved volumetric analysis.

Project Page | Code

GaussianNeRF: High-Fidelity Surface Reconstruction based on Gaussian Constraint

We enhanced NeRF’s mesh modeling quality and speed by incorporating a Gaussian loss function, resulting in better mesh quality and outperforming Nerfacto in texture and runtime.

Report

GPT-ID: GPT Interaction Detector

We propose GPT-ID, a tool built upon DetectGPT, designed to distinguish AI-generated from human-written texts with improved accuracy and novel edit distribution comparison, aiming to ensure responsible use of text-generation technologies.

Report

Store Sales - Time Series Forecasting

The project aims to forecast sales for Ecuador’s Corporación Favorita using time series data, achieving top 5 leaderboard ranking through data analysis, Exponential Smoothing, LightGBM, and Genetic Mutation algorithms.

Kaggle Competition | Report

Undergraduate Thesis: A Radar Signal Sorting and Locating Approach Based on UAV Swarm via Distributed Algorithm

Traditional methods using Pulse Descriptor Word (PDW) for radar signal sorting and locating are limited in accuracy, but our new SDSL framework, utilizing the PP-YOLOE model, improves performance and efficiency, especially for UAV swarms.

Paper | Poster | Patent

Experience

Research Engineer

Aug 2023 - Present

Supervisor: Dr. Andrew Feng

USC Institute for Creative Technologies

Supervisor: Dr. Andrew Feng

Aug 2023 - Present

Research Assistant

Aug 2023 - May 2024

Supervisor: Dr. Andrew Feng

USC Institute for Creative Technologies

Supervisor: Dr. Andrew Feng

Aug 2023 - May 2024

  • 3D Gaussian Splatting
  • Atomizing Gaussian Splatting for High-Fidelity Radiance Field

Research Intern

May 2023 - Aug 2023

Supervisor: Dr. Andrew Feng

USC Institute for Creative Technologies

Supervisor: Dr. Andrew Feng

May 2023 - Aug 2023

  • Neural Radiance Fields (NeRF)
  • Scalable NeRF on large terrain datasets

Research Assistant

July 2020 - July 2022

Supervisor: Prof. Liangtian Wan

Dalian University of Technology

Supervisor: Prof. Liangtian Wan

July 2020 - July 2022

  • Objective Detection (RCNN and YOLO)
  • Transfer Learning

Teaching Assistant

September 2021 - June 2022

Dalian University of Technology

September 2021 - June 2022

  • Program Design Basics and C Programming
  • Object-Oriented Method and C++ Program Design

Awards