Mingyang Xie 谢铭阳

I am currently a 4th year Ph.D. student at the University of Maryland, advised by Christopher Metzler. Previously, I obtained my Bachelor degree from Washington University in St. Louis, advised by Ulugbek Kamilov and Brendt Wohlberg.

I am broadly interested in computer vision and machine learning, with a focus on computational photography and generative AI. I am actively looking for research internships for 2025.

CV Scholar LinkedIn Email

Publications (* denotes equal contribution)

Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats

Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats

Mingyang Xie*, Haoming Cai*, Sachin Shah, Yiran Xu, Brandon Y. Feng, Jia-Bin Huang, Christopher Metzler
ECCV 2024

We introduce a simple yet effective approach for separating transmitted and reflected 3D scenes by using Gaussian Splatting and unpaired flash and no-flash multi-view images.

Project Page
WaveMo: Learning Wavefront Modulations to See Through Scattering

WaveMo: Learning Wavefront Modulations to See Through Scattering

Mingyang Xie*, Haiyun Guo*, Brandon Y. Feng, Lingbo Jin, Ashok Veeraraghavan, Christopher Metzler
CVPR 2024

Use a proxy reconstruction network to learn an optimal set of wavefront modulation patterns in an end-to-end fashion.

Project Page arXiv PDF
Snapshot High-Dynamic-Range Imaging with a Polarization Camera

Snapshot High-Dynamic-Range Imaging with a Polarization Camera

Mingyang Xie*, Matthew Chan*, Christopher Metzler
Preprint, 2023 ICCP 2023 Poster Demo

A novel single-shot HDR imaging methodology using a polarization camera, achieving 4dB improvement over software-only baselines.

Project Page arXiv PDF
NeuWS: Neural Wavefront Shaping for Guidestar-Free Imaging Through Static and Dynamic Scattering Media

NeuWS: Neural Wavefront Shaping for Guidestar-Free Imaging Through Static and Dynamic Scattering Media

Brandon Y. Feng*, Haiyun Guo*, Mingyang Xie, Vivek Boominathan, Manoj K. Sharma, Ashok Veeraraghavan, Christopher Metzler
Science Advances 2023 Science.org Frontpage Cover

Neural signal representations enable breakthroughs in correcting for severe time-varying wavefront aberrations caused by scattering media.

PDF Code
TurbuGAN: An Adversarial Learning Approach to Spatially-Varying Multiframe Blind Deconvolution with Applications to Imaging Through Turbulence

TurbuGAN: An Adversarial Learning Approach to Spatially-Varying Multiframe Blind Deconvolution with Applications to Imaging Through Turbulence

Brandon Y. Feng*, Mingyang Xie*, Christopher Metzler
IEEE Journal on Selected Areas in Information Theory, 2022

Training GAN only on blurry images from a single scene to recover a sharp image without estimating the blur kernels or acquiring a large labelled dataset.

arXiv PDF
CoIL: Coordinate-Based Internal Learning for Tomographic Imaging

CoIL: Coordinate-Based Internal Learning for Tomographic Imaging

Yu Sun, Jiaming , Mingyang Xie, Brendt Wohlberg, Ulugbek Kamilov
IEEE Transactions on Computational Imaging, 2021

Learning the computed tomography measurement field by mapping X-ray angles to corresponding pixel values using implicit neural representation.

arXiv PDF
Joint Reconstruction and Calibration Using Regularization by Denoising with Application to Computed Tomography

Joint Reconstruction and Calibration Using Regularization by Denoising with Application to Computed Tomography

Mingyang Xie*, Jiaming Liu*, Yu Sun, Brendt Wohlberg, Ulugbek Kamilov
ICCV Workshop, 2021

A regularization by denoising approach for image reconstruction tasks where there exist parametric uncertainties in the imaging forward model.

arXiv PDF
PROVES: Establishing Image Provenance using Semantic Signatures

PROVES: Establishing Image Provenance using Semantic Signatures

Mingyang Xie, Manav Kulshrestha, Shaojie Wang, Jinghan Yang, Ayan Chakrabarti, Ning Zhang, Yevgeniy Vorobeychik
WACV, 2022

Using semantic signing for image verification against deep fake attacks.

arXiv PDF