Di Liu
Ph.D. student @ Rutgers | di.liu@rutgers.edu

I am a Ph.D. student in the Department of Computer Science at Rutgers University, advised by Distinguished Professor Dimitris Metaxas. Prior to this, I was a Research Assistant in the Department of Electrical and Computer Engineering at The Johns Hopkins University.

My current research interests lie primarily in (1) Shape representation and scene understanding; (2) multimodal object detection and segmentation.

  |     |  


Education

Sept. 2021 - Present
Rutgers Univeristy
Ph.D. Student in Computer Science (GPA: 4.0/4.0)
Jan. 2020 - Aug. 2021
The Johns Hopkins University
Research Assistant in Electrical and Computer Engineering
Sept. 2018 - Jun. 2021
Beijing Institute of Technology
M.S. in Information and Communication Engineering (GPA: 4.0/4.0)

Experience

Sept. 2021 - Present
Rutgers University. Piscataway, NJ, USA
Research Assistant. Advisor: Prof. Dimitris N. Metaxas
  • Deformable 3D Gaussian Splats for Dynamic Object Reconstruction from Videos.
  • Scene Decomposition and Reasoning with Large Language Models (LLMs).
  • Layout-Agnostic Scene Text Image Synthesis with Integrated Character-Level Diffusion Models.
  • Scaling Panoptic Segmentation with Multi-dataset Training and Part-whole Awareness.
Jan. 2024 - Present
Cognition, Cloud & AI, Microsoft. Redmond, WA, USA
Research Intern. Host: Dr. Dongdong Chen
  • Large-scale Multi-modality Pretraining and Fundamental Models for Scene Understanding.
May. 2023 - Aug. 2023
Media Analytics, NEC Labs America. San Jose, CA, USA
Research Intern. Host: Dr. Manmohan Chandraker
  • Instantaneous Perception of Fine-grained 3D Motion.
Jun. 2022 - Sept. 2022
SenseTime. San Jose, CA, USA
Research Intern. Host: Dr. Mu Zhou
Jan. 2020 - Aug. 2021
The Johns Hopkins University. Baltimore, MD, USA
Research Assistant. Advisor: Prof. Jerry L. Prince
  • Label Super Resolution for 3D Magnetic Resonance Images.[SPIE'21]
  • Domain Adaptation and Automatic Identification of Circulating Tumor Cells (CTC).
Sept. 2018 - Dec. 2019
Beijing Institute of Technology. Beijing, China
Research Assistant. Advisor: Prof. Ran Tao
  • Dispersion Correction for Optical Coherence Tomography (OCT) using Fractional Fourier Transform.[Optics Express, ICMA'19]
  • Automated Recognition of Arrhythmia with Fractional Time–frequency Domain Extension. [JMIHI]

Selected Publications

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction
Di Liu, Qilong Zhangli, Yunhe Gao, Dimitris N. Metaxas.
NeurIPS 2023
[Paper] [Bibtex]
DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image
Di Liu, Xiang Yu, Meng Ye, Qilong Zhangli, Zhuowei Li, Zhixing Zhang, Dimitris N. Metaxas.
ICCV 2023
[Paper] [Bibtex]
Learning Explicit Shape Abstractions with Deep Deformable Models
Di Liu, Xiang Yu, Long Zhao, Ting Liu, Dimitris Metaxas
TPAMI(under review)
[Paper] [Bibtex]
Deep Deformable Models: Learning 3D Shape Abstractions with Part Consistency
Di Liu, Long Zhao, Yunhe Gao, Qilong Zhangli, Ting Liu, Dimitris Metaxas
arXiv
[Paper] [Bibtex]
Improving Negative-Prompt Inversion via Proximal Guidance
Ligong Han, Song Wen, Qi Chen, Zhixing Zhang, Kunpeng Song, Mengwei Ren, Ruijiang Gao, Yuxiao Chen, Di Liu, Dimitris N. Metaxas
arXiv
[Paper] [Bibtex]
Training Like a Medical Resident: Universal Medical Image Segmentation via Context Prior Learning
Yunhe Gao, Zhuowei Li, Di Liu, Mu Zhou, Shaoting Zhang, Dimitris N. Metaxas
arXiv
[Paper] [Bibtex]
Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge Distillation
Xiaoxiao He, Chaowei Tan, Bo Liu, Liping Si, Weiwu Yao, Liang Zhao, Di Liu, Qilong Zhangli, Qi Chang, Kang Li, Dimitris N. Metaxas
ISBI 2023
[Paper] [Bibtex]
Steering Prototype with Prompt-tuning for Rehearsal-free Continual Learning
Zhuowei Li, Long Zhao, Zizhao Zhang, Han Zhang, Di Liu, Ting Liu, Dimitris N. Metaxas
arXiv
[Paper] [Bibtex]
A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark
Yunhe Gao, Mu Zhou, Di Liu, Zhennan Yan, Dimitris Metaxas
TPAMI(under review)
[Paper] [Bibtex]
TransFusion: Multi-view Divergent Fusion for Medical Image Segmentation with Transformers
Di Liu, Yunhe Gao, Qilong Zhangli, Zhennan Yan, Mu Zhou, Dimitris Metaxas
MICCAI 2022
[Paper] [Bibtex]
Region Proposal Rectification Towards Robust Instance Segmentation of Biological Images
Qilong Zhangli, Jingru Yi, Di Liu, Xiaoxiao He, Zhaoyang Xia, Haiming Tang, He Wang, Mu Zhou, Dimitris Metaxas
MICCAI 2022
[Paper] [Bibtex]
DeepRecon: Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via A Structure-Specific Generative Method
Qi Chang, Zhennan Yan, Mu Zhou, Di Liu, Khalid Sawalha, Meng Ye, Qilong Zhangli, Mikael Kanski, Subhi Al Aref, Leon Axel, Dimitris Metaxas
MICCAI 2022
[Paper] [Bibtex]
Refined Deep Layer Aggregation for Multi-Disease, Multi-View & Multi-Center Cardiac MR Segmentation
Di Liu, Zhennan Yan, Qi Chang, Leon Axel, Dimitris Metaxas
MICCAI 2021
[Paper] [Bibtex]
Label Super Resolution for 3D Magnetic Resonance Images using Deformable U-Net
Di Liu, Jiang Liu, Yihao Liu, Ran Tao, Jerry L. Prince, Aaron Carass
SPIE 2021
[Paper] [Bibtex]
Dispersion correction for optical coherence tomography by the stepped detection algorithm in the fractional Fourier domain
Di Liu, Chuanbin Ge, Yi Xin, Qin Li, Ran Tao
Optics Express
[Paper] [Bibtex]
Automated Recognition of Arrhythmia Using Deep Neural Networks for 12-Lead Electrocardiograms with Fractional Time–Frequency Domain Extension
Chuanbin Ge, Di Liu, Juan Liu, Bingshuai Liu, Yi Xin
JMIHI
[Paper] [Bibtex]
Dispersion Correction for Optical Coherence Tomography by Parameter Estimation in Fractional Fourier Domain
Di Liu, Yi Xin, Qin Li, Ran Tao
ICMA 2019
[Paper] [Bibtex]

Templete stolen from Jon Barron and Georgia Gkioxari