Sijie Ding

I am a second-year PhD student at Stony Brook University.

Previously, I obtained my master's degree at Brown University, advised by Prof. Srinath Sridhar. I earned my bachelor's degree at Rutgers University.

I'm interested in 3D computer vision and machine learning.

Email  /  Google Scholar  /  Twitter  /  LinkedIn

profile photo
Publications
Fast-4DGS: Fast 4D Gaussian Representation for Real-Time Novel View Synthesis using Monocular RGB Images
Sijie Ding, Yoonsang Kim, Arie Kaufman
Under submission
Volumetric Reconstruction for the Visualization of 3D Anatomical Structures from Limited Number of X-rays
Gaofeng Deng, Sijie Ding, Arie Kaufman
Under submission
LEGO-Net: Learning Regular Rearrangements of Objects in Rooms
Qiuhong Anna Wei, Sijie Ding, Jeong Joon Park, Rahul Sajnani, Adrien Poulenard, Srinath Sridhar, Leonidas Guibas
CVPR 2023
website / arxiv / code

LEGO-Net is a data-driven transformer-based iterative method for LEarning reGular rearrangement of Objects in messy rooms. LEGO-Net is partly inspired by diffusion models – it starts with an initial messy state and iteratively “de-noises” the position and orientation of objects to a regular state while reducing distance traveled.

Toward Fully Automated Metal Recycling using Computer Vision and Non-Prehensile Manipulation
Shuai D. Han, Baichuan Huang, Sijie Ding, Changkyu Song, Si Wei Feng, Ming Xu, Hao Lin, Qingze Zou, Abdeslam Boularias, Jingjin Yu
2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)
paper / video / code

In this work, leveraging the latest development in machine learning and robot learning, we develop an image-based sorting system for tackling this challenging task.

Monitoring and detection of meltpool and spatter regions in laser powder bed fusion of super alloy Inconel 625
Lihang Yang, Lydia Lo, Sijie Ding, Tuğrul Özel
Progress in Additive Manufacturing, 5, 367–378 (2020)
poster

The results indicate that some occurrences of undermelting, overmelting, and material spatter can be detected that can then be correlated to localized defects, delamination, and layer separation.


source code of this website