Nice to meet you
I am Linda, a hardware sensing engineer at Everyday Robots developing robotic sensing architecture, cameras, depth sensors and thermal sensors. Before this, I received my PhD from EECS department at UC Berkeley advised by Prof. Laura Waller. My PhD research focused on computational optics, which is a combination of optical hardware, physical modeling, optimization algorithms, and machine learning.

Research Projects

Physics-based learning: Algorithms and optics co-design

Eric Markley*, Fanglin Linda Liu*(equal contribution), Michael Kellman, Nick Antipa, and Laura Waller
NeurIPS 2021 Workshop on Deep Learning and Inverse Problems

We use a differentiable forward model of single-shot 3D microscopy in conjunction with an invertible and differentiable reconstruction algorithm, ISTA-Net⁺, to jointly optimize both the diffuser surface shape and the reconstruction parameters for Fourier DiffuserScope. By choosing a differentiable and invertible reconstruction method, we enable the use of memory-efficient backpropagation to trade off storage with a reasonable increase in compute time, in order to fit an unrolled network containing a large-scale 3D volume into a single GPU's memory.

Fourier DiffuserScope: Single-shot 3D Microscopy with a diffuser

Fanglin Linda Liu, Grace Kuo, Nick Antipa, Laura Waller
Optics Express 28, 28969 (2020)

We demonstrate improved resolution across a large volume with Fourier DiffuserScope, which uses a diffuser in the pupil plane to encode 3D information, then computationally reconstructs the volume by solving a sparsity-constrained inverse problem. Our diffuser consists of randomly placed microlenses with varying focal lengths; the random positions provide a larger field-of-view compared to a conventional microlens array, and the diverse focal lengths improve the axial depth range.

On chip fluorescence microscopy with a random microlens diffuser

Grace Kuo, Fanglin Linda Liu, Kristina Monakhova, Kyrollos Yanny, Ren Ng, Laura Waller
Optics Express 28, 8384 (2020)

We present an on-chip, widefield fluorescence microscope, which consists of a diffuser placed a few millimeters away from a traditional image sensor. The diffuser replaces the optics of a microscope, resulting in a compact and easy-to-assemble system with a practical working distance of over 1.5 mm. Furthermore, the diffuser encodes volumetric information, enabling refocusability in post-processing and 3D imaging of sparse samples from a single acquisition.

Work Experience

Everyday Robots, (Google) X, the the moonshot factory

Hardware sensing engineer, 02/2022 – Current
Project Silica, Microsoft Research

Optical engineer intern, 12/2020 – 03/2021