Zhihao (Zach) 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: I'm always happy to host research interns at Adobe. If you are interested in interning with me, please send me an email describing your past experience and current research interests.

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.

Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos
Hadi AlZayer, Zhihao Xia, Xuaner Zhang, Eli Shechtman, Jia-Bin Huang, Michaël Gharbi
Arxiv, 2024
project page/ paper/ code

A generative model that, given a coarsely edited image, synthesizes a photorealistic output that follows the prescribed layout.

Explorative Inbetweening of Time and Space
Haiwen Feng, Zheng Ding, Zhihao Xia, Simon Niklaus, Victoria Abrevaya, Michael J. Black, Xuaner Zhang
ECCV, 2024
project page/ paper/ code

Control pre-trained video generation models to synthesize arbitrary camera and subject motion based only on a given start and end frame.

Restoration by Generation with Constrained Priors
Zheng Ding, Xuaner Zhang, Zhuowen Tu, Zhihao Xia
CVPR, 2024
project page/ paper/ code

A method to directly apply a pre-trained diffusion model to blind image restoration, by constraining the generative space using a set of anchor images.

Self-Supervised Burst Super-Resolution
Goutam Bhat, Michaël Gharbi, Jiawen Chen, Luc Van Gool, Zhihao Xia
ICCV, 2023
paper

A self-supervised training strategy for burst super-resolution that only uses noisy low-resolution bursts during training.

DiffusionRig: Learning Personalized Priors for Facial Appearance Editing
Zheng Ding, Xuaner Zhang, Zhihao Xia, Lars Jebe, Zhuowen Tu, Xiuming Zhang
CVPR, 2023
project page / paper / video / code

A custom diffusion model that can "rig" the lighting, facial expression, and head pose in a portrait photo while maintaining identity and preserving high-frequency features.

Semi-supervised Parametric Real-world Image Harmonization
Ke Wang, Michaël Gharbi, He Zhang, Zhihao Xia, Eli Shechtman
CVPR, 2023
project page / paper

A parametric harmonization method employing semi-supervised training to learn local appearance harmonization from unpaired real composites.

Neural Photo-Finishing
Ethan Tseng, Yuxuan Zhang, Lars Jebe, Xuaner Zhang, Zhihao Xia, Yifei Fan,
Felix Heide*, Jiawen Chen*
SIGGRAPH Asia, 2022
project page / paper / supplement

An end-to-end differentiable pipeline for rendering sRGB images from raw inputs controlled by meaningful parameters.

Handheld Multi-Frame Neural Depth Refinement
Ilya Chugunov, Yuxuan Zhang, Zhihao Xia, Xuaner Zhang, Jiawen Chen, Felix Heide,
CVPR, 2022   (Oral Presentation)
project page / arxiv / code

High-fidelty depth recovery for tabletop objects from a single smartphone shot.

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

Face surface normal and reflectance estimation under uncontrolled visible lighting with 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

A basis prediction network that predicts global basis kernels and corresponding per-pixel coefficients for burst denoising.

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

A common model that is only trained once for a variety of monocular depth applications.

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

Image denoising by using DNN to exploit self-similarity in natural images.

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

Unsupervised framework for training image estimation networks from only degraded or partial measurements.

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

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