Zhihao Xia

I am a research scientist on Marc Levoy's computational photography team at Adobe, where I work on computer vision, computational photography and machine learning.

I received my PhD from WashU advised by Ayan Chakrabarti. Prior to WashU, I got my Bachelors from School of the Gifted Young at USTC. I've also spent time at research labs at Google Research, Adobe Research, NUS and KAUST.

Internships: We are actively hiring for research interns for summer 2022. Please email me if you are interested in working with us at Adobe!

Email  /  CV  /  Google Scholar /  GitHub

Research

My research interests include computer vision, computational photography and deep learning. I am particularly interested in the design of accurate and efficient algorithms for visual inference --- reasoning different aspects of visual appearance (geometry, light, colors, etc) from images and videos.

A Dark Flash Normal Camera
Zhihao Xia, Jason Lawrence, Supreeth Achar
ICCV, 2021
project page / arxiv / video

Estimating surface normal and reflectance maps of people under uncontrolled and challenging visible lighting, by supplementing the available visible illumination with a controlled single near infrared (NIR) light source and camera, i.e., a "dark flash image".

Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments
Zhihao Xia, Michaël Gharbi, Federico Perazzi, Kalyan Sunkavalli, Ayan Chakrabarti
CVPR, 2021
project page / arxiv / code / video

A neural network-based method to denoise pairs of images taken in quick succession in low-light environments, with and without a flash.

Basis Prediction Networks for Effective Burst Denoising with Large Kernels
Zhihao Xia, Federico Perazzi, Michaël Gharbi, Kalyan Sunkavalli, Ayan Chakrabarti
CVPR, 2020
project page / arxiv / code / video

We introduce a novel basis prediction network that predicts a set of global basis kernels and the corresponding per-pixel mixing coefficients to denoise noisy bursts from cellphone cameras.

Generating and Exploiting Probabilistic Monocular Depth Estimates
Zhihao Xia, Patrick Sullivan, Ayan Chakrabarti
CVPR, 2020   (Oral Presentation)
project page / arxiv / code / video

Propose a common model that is only trained once for a variety of depth applications, including monocular depth estimation, depth estimation with user interaction, depth completion, etc.

Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising
Zhihao Xia, Ayan Chakrabarti
WACV, 2020
project page / arxiv / code

Exploit self-similarity or recurring patterns (internal statistics) with deep neural networks (external statistics) for natural image denoising.

Training Image Estimators without Image Ground-Truth
Zhihao Xia, Ayan Chakrabarti
NeurIPS, 2019   (Spotlight)
project page / arxiv / code

Introduce an unsupervised framework for training image estimation networks, from only degraded or partial measurements, but no ground-truth and even no measurement parameter (e.g., blurring kernel).

DeeReCT-PolyA: a robust and generic deep learning method for PAS identification
Zhihao Xia, Yu Li, Bin Zhang, Zhongxiao Li, Yuhui Hu, Wei Chen, Xin Gao
Bioinformatics, 2018
supplement / code

A robust deep learning model for the identification of polyadenylation signal - a critical factor for gene expression.

Efficient and accurate inversion of multiple scattering with deep learning
Yu Sun, Zhihao Xia, Ulugbek S. Kamilov
Optics Express, 2018

Propose a deep convolutional neural network for image reconstruction under multiple light scattering.

Teaching
CV2018

CSE559A: Computer Vision - Fall 2018
Teaching Assistant


This webpage is cool