Research Aide - LCF - Islam, Md Robiul - 3.20.26.
About The Position
Large-scale scientific simulations generate massive datasets that are challenging to visualize interactively, particularly on lightweight devices. Recent advances in 3D Gaussian Splatting (3D-GS) have shown impressive scalability for large, image-based scene reconstruction through hierarchical level-of-detail (LOD) representations and parallel training strategies.This project explores whether this technique can be adapted to scientific visualization to enable multi-scale interactive rendering of large-scale scientific data. The student will implement a pipeline that generates thousands of zoom-in and zoom-out images from simulation outputs, trains hierarchical 3D Gaussian models, and evaluates their performance for interactive visualization. The project will include a comparative study against an alternative scalable approach (e.g., Grendel-GS style parallel training), focusing on tradeoffs between training scalability, runtime performance, memory usage, and visual behavior across zoom levels. The outcome is expected to be a research poster or a short paper, providing insight into the feasibility and limitations of applying 3D Gaussian splatting techniques to large-scale scientific data. Education and Experience Requirements The entirety of the appointment must be conducted within the United States. Applicants must be: o Currently enrolled in undergraduate or graduate studies at an accredited institution. o Graduated from an accredited institution within the past 3 months; or o Actively enrolled in a graduate program at an accredited institution. Must be 18 years or older at the time the appointment begins. Must possess a cumulative GPA of 3.0 on a 4.0 scale. If accepting an offer, candidates may be required to complete pre-employment drug testing based on appointment length. All students remain subject to applicable drug testing policies. Must complete a satisfactory background check.
Requirements
- The entirety of the appointment must be conducted within the United States.
- Currently enrolled in undergraduate or graduate studies at an accredited institution.
- Graduated from an accredited institution within the past 3 months; or
- Actively enrolled in a graduate program at an accredited institution.
- Must be 18 years or older at the time the appointment begins.
- Must possess a cumulative GPA of 3.0 on a 4.0 scale.
- If accepting an offer, candidates may be required to complete pre-employment drug testing based on appointment length. All students remain subject to applicable drug testing policies.
- Must complete a satisfactory background check.
Responsibilities
- Implement a pipeline that generates thousands of zoom-in and zoom-out images from simulation outputs
- Train hierarchical 3D Gaussian models
- Evaluate performance for interactive visualization
- Conduct a comparative study against an alternative scalable approach
- Create a research poster or short paper
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Intern
Education Level
No Education Listed
Number of Employees
1,001-5,000 employees
