Samir Agarwala

I am an alumnus of the MS CS program at Stanford University where I worked in computer vision.

I am grateful to have worked with Jiajun Wu and Leonidas Guibas during my MS and completed my undergraduate education at the University of Michigan where I was fortunate to be advised by David Fouhey.

Before starting research in mainstream vision, I had the privilege of working with Amy Cohn and Stephen Parker at Michigan where I worked on healthcare operations research and bioinformatics respectively.

Email  /  CV  /  Google Scholar  /  Github

profile photo
Research

I am interested in developing robust computer vision systems that can understand the world around us. Some areas of particular interest include scene understanding, learning robust visual representations and models using unstructured visual data, and neural rendering.

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark
Zhengfei Kuang*, Yunzhi Zhang*, Hong-Xing Yu, Samir Agarwala, Shangzhe Wu, Jiajun Wu
NeurIPS (Datasets and Benchmarks), 2023
project page / arXiv

A novel real-world object inverse rendering benchmark to evaluate inverse rendering methods.

Accidental Light Probes
Hong-Xing Yu, Samir Agarwala, Charles Herrmann, Richard Szeliski, Noah Snavely, Jiajun Wu, Deqing Sun
CVPR, 2023
project page / arXiv

Specular objects such as coke cans often appear "accidentally" in images and can be used to recover scene lighting from single image observations using differentiable rendering.

PlaneFormers: From Sparse View Planes to 3D Reconstruction
Samir Agarwala, Linyi Jin, Chris Rockwell, David F. Fouhey
ECCV, 2022
project page / arXiv

Transformers are really good at integrating evidence across multiple views and producing a planar reconstruction.

Using Discrete-Event Simulation to Analyze the Impact of Variation on Surgical Training Programs
Fumiya Abe-Nornes, Samir Agarwala, Nathan Smith, Rachel Zhang, Amy Cohn, Angela Thelen, Rishindra Reddy, Brian George
WSC, 2022
Paper

Real-life variation in learning speeds of surgical trainees and decrease in available training opportunities can affect trainee competency and potentially endager patient safety.

RFX6-mediated dysregulation defines human β cell dysfunction in early type 2 diabetes
JT Walker*, DC Saunders*, V Rai*, C Dai, P Orchard, AL Hopkirk, CV Reihsmann, Y Tao, S Fan, S Shrestha, A Varshney, JJ Wright, YD Pettway, C Ventresca, Samir Agarwala, R Aramandla, G Poffenberger, R Jenkins, NJ Hart, DL Greiner, LD Shultz, R Bottino, Human Pancreas Analysis Program, J Liu, SCJ Parker, AC Powers, M Brissova
bioRxiv, 2021
bioRxiv

Identifying early disease-driving events of type 2 diabetes through integrative analysis of diverse modalities.


Website based on Jon Barron's website