I am a computer science Ph.D. candidate at the Harvard School of Engineering and Applied Sciences, working with Todd Zickler. I am also currently a student researcher at Google Research, working with Jon Barron, Pratul Srinivasan, Peter Hedman, and Ben Mildenhall.

Research Focus:

I am interested in computer vision algorithms that are informed by geometry, physics, and graphics. By incorporating domain-specific constraints into differentiable architectures, I aim to improve the efficiency, generalizability , and interpretability of artificial vision systems.

Selected Projects:

Ref-NeRF
Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields
CVPR, 2022 (Oral Presentation, Best Student Paper Honorable Mention)
 
Neural radiance fields (NeRF) often produces incorrect specular highlights. We modify NeRF's representation of view-dependent appearance to fix that problem, and recover accurate surface normals. Our method also enables view-consistent scene editing.
FoJ
Field of Junctions: Extracting Boundary Structure at Low SNR
Dor Verbin, Todd Zickler
ICCV, 2021
 
By modeling each patch in an image as a generalized junction, our model uses concurrencies between different boundary elements such as junctions, corners, and edges, and manages to extract boundary structure from extremely noisy images where previous methods fail.
Chair SFT
Toward a Universal Model for Shape from Texture
Dor Verbin, Todd Zickler
CVPR, 2020
 
We formulate the shape from texture problem as a 3-player game. This game simultaneously estimates the underlying flat texture and object shape, and it succeeds for a large variety of texture types.
SFT Uniqueness
Unique Geometry and Texture from Corresponding Image Patches
TPAMI, 2021
 
We present a simple condition for the uniqueness of a solution to the shape from texture problem. We show that in the general case four views of a cyclostationary texture satisfy this condition and are therefore sufficient to uniquely determine shape.