Xiaochen Zhou

I am a third-year PhD student at Purdue University, where I major in computer graphics, computer vision, image processing and machine learning. I am a research assistant in HPCG Lab, advised by Bedrich Benes.

I graduated from Washington University in st. Louis with a Master degree and I defensed my bachelor degree at Beihang University. I achieved amazing internship experience in Microsoft, Meta and Megvii Face++.

Email  /  CV  /  Research Interests  /  LinkedIn  /  Github

I'm interested in computer vision, machine learning, optimization, and image processing. More specifially, I'm interested in 3D modeling and reconstruction.

We designed a new modeling architecture for urban modeling. We provided the real-time local editing tools called atomic brushes to edit the elements of the local region in the urban city.

This project is the master defense project. We firstly extract the layout of the source image with additional information. Second, the layout image is extended via optimized patch matching algorithms. Then we implemented coarse-to-fine progressive Unet GAN to reconstruct the completed image through layouts.

In this project, a generative adversial network is trained to generate and edit image through contour domain, where canny edge detection is used to extract contour information through original input.

Two score units are devised to evaluate the quality of each projected image with score vectors.

A novel deep neural network, recurrent panorama network (RePanoNet), is designed to extract features in a panoramic view, encouraging the network to recognize the original 3D shape.

We designed an encoder-decoder recurrent feature aggregation network (ERFA-Net) to emphasize the 3D properties of 3D shapes in multi-view features aggregation.

Great thank for the website template!