About Me

I am a second-year graduate student in Computer Science at the University of Maryland, College Park advised by Professor Tom Goldstein. I transferred to the PhD program in Spring 2025 after completing my BS/MS in Computer Science in 2024.

I am broadly interested in the intersection of deep learning, computer vision, and graphics. My recent work focuses on 3D scene reconstruction, and I am currently funded by the IARPA Walk-through Rendering from Images of Varying Altitude (WRIVA) program. Additionally, I have research and teaching experience in multimodal biometric recognition, large language models, vision encoders, generative adversarial networks, image quality metrics, and visualization recommendation.

News

• November 2024: Updated our PUP 3D-GS website, preprint, and code.
• November 2024: Released our Speedy-Splat website, preprint, and code.
• November 2024: Officially transferring into the PhD program in Spring 2025!
• June 2024: Released our PUP 3D-GS website, preprint, and code.
• May 2024: Returned to STR as a Computer Vision Research Intern.
• May 2024: Finished my BS/MS in Computer Science at UMD! 🎉
  Extended to transfer into the PhD program in Spring 2025.

Research Highlights

Hover to zoom in and play media, * indicates equal contribution.

	Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives Preprint, 2024. PAPER CODE Accelerate 3D Gaussian Splatting rendering speed by over 6× and reduce model size by over 90% through accurately localizing primitives during rasterization and pruning the scene during training, providing a significantly higher speedup than existing techniques while maintaining competitive image quality. Alex Hanson, Allen Tu, Geng Lin, Vasu Singla, Matthias Zwicker, Tom Goldstein
	PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting 🐶 Preprint, 2024. PAPER CODE Prune 90% of primitives from any pretrained 3D Gaussian Splatting model using a mathematically principled sensitivity score, more than tripling rendering speed while retaining more salient foreground information and higher visual fidelity than previous techniques at a substantially higher compression ratio. Alex Hanson*, Allen Tu*, Vasu Singla, Mayuka Jayawardhana, Matthias Zwicker, Tom Goldstein
Predict and Aggregate [1, 2] improves the CMC and ROC performance of the SOTA face recognition system by an empirical upper bound of 11.54% at the evaluation thresholds.	IARPA Biometric Recognition and Identification at Altitude and Range (BRIAR) Systems & Technology Research, 2022-2024. I researched face recognition, body recognition, and multimodal fusion for our SOTA system. Ask me about: Knowledge distillation for face probe-to-gallery feature similarity prediction. (2024) Feature clustering and aggregation for face recognition from videos. (2024) Training operating condition-invariant face encoders. (2023) Model ensembling and mixed-voting classifiers for open search. (2023) Data augmentation via garment transfer for training clothing-invariant body encoders. (2022) Mentors: Dr. Jennifer Xu, Prof. Vishal Patel, Prof. Rama Chellappa, Noam Eshed, Matthew Meyn, Dr. Mark Keck, Dr. Nathan Shnidman

Related Experience

I am always open to collaborations — please email me if you would like to chat or get involved!
See my CV for full details and other experiences.