- Cross-video neural representations (CURE) for video interpolation was accepted to the ECCV2022! @ Jul 3 2022
- I am going to start Ph.D. at Boston University dvised by Prof. Goyal in this fall! @ Apr 4 2022
- Successfully defended my MS thesis! @ Dec 1 2021
I am a research assistant in ECE at Washington University in St. Louis with Professor Matthew Lew. Before that, I was a master student in the Computational Imaging Group with Prof. Ulugbek Kamilov. I worked on computer vision and deep learning algorithms. Specifically, I proposed the first neural field (NF) based video frame interpolation algorithm.
In 2019, I worked as a visiting research assistant at Center for Optoelectronic Technology, SIAT. SIAT is a cool place where engineers and researchers made many brilliant products. I focus on the design and building of in-situ chemical oxygen demand (COD) sensor for long-term seawater monitoring. SIAT is where arouse my interest of optical systems. Prior to that, I did my BS in NCU with Prof. Qiurong Yan. We built a single photon compressed imaging system with digital micromirror device (DMD) and photomultiplier tube (PMT). It is a cool system that let me know how diverse the optical imaging system could be.
I love imaging and computer vision (CV). I believe it is important to collaboratively develop imaging systems and CV algorithms. This is where a lot of high quality innovations were crteated. My current research interests include computational imaging, inverse problems, Machine learning, Implicit neural representations, neural video representations, video processing, video interpolation, computer vision, and so on.
Besides that, I enjoy playing a violin, hiking, taking photoes, and making videos. Those hobbies make me calm down or inspire me when I was trapped down. My favourate masterpiece is TCHAIKOVSKY’s Violin Concerto in D major, op. 35.
wentaos [at] bu [dot] edu
Learning Cross-Video Neural Representations for High-Quality Frame Interpolation
Wentao Shangguan, Yu Sun, Weijie Gan, Ulugbek S. Kamilov
NeVR: Learning Continuous Neural Video Representation with Local Feature Codes for Video Interpolation
Washington University in St. Louis - dissertation
Adaptive Single Photon Compressed Imaging Based on Constructing a Smart Threshold Matrix
Wentao Shangguan, Qiurong Yan, Hui Wang, Chenglong Yuan, Bing Li andYuhao Wang
Sensors, 18, 10, 3449
Learning Cross-Video Neural Representations for High-Quality Frame Interpolation 2022
Cross-Video Neural Representation (CURE) is a Deep-learning-based model for temporal video interpolation, where the goal is to synthesize a new video frame given its two neighbors. It is the first video interpolation method based on neural fields (NF) and achieves the state-of-the-art performance on video interpolation on several benchmark datasets.
Underwater spectrophotometer for in-situ seawater COD monitoring 2019
We designed an in-situ chemical oxygen demand (COD) sensor for long-term seawater monitoring, and interrated it to a buoy for coastal trials. It makes COD monitoring becomes possible and simple. The sensors had been contiously working underwater for more than 6 months and provides thousands of valuable UV-Vis absorption spectrum.
Adaptive Single Photon Compressed Imaging Based on Constructing a Smart Threshold Matrix 2018
Single photon imaging system is a photon counting based singel pixel camera, which takes picture with compressed sensing (CS) theory. We proposed an smart adaptive measurement matrix to improve the performance of CS reconstruction ability. The experiement shows our smart matrix could work for many algorithms and could be used for modify any kind of measurement matrix.
Three Phase DC-AC Converter 2017
This three phase DC-AC converter aims for converting 12V DC power to three phase 24V AC power. This system is controlled by a STM32F103 Microcontrol Unit, which provides features like voltage regulation, phase regulation, over-current protection. The efficiency is higher than 90%. Phase regulation enables two converter grid-connected. The output voltage is regulated with PID algorithm for 100 times per second.
Wireless Auto-Detection Electromagnetic Gun 2017
In this small project, I designed and made a wireless electromagnetic gun. Both radio and gun are built with STM32F103. The radio could show the current voltage, firing status, and could auto detect object near it. When the object approaching, it will send fire signal to the electromagnetic gun through 2.4G NFR24L01. The controller has two buttons that user could use for manually firing. The electromagnetic gun is powered by two XL6009 that transfer 12V DC to ~70V DC. Two capacitances are used to store the power. The steel ball could be ejected for ~30 feets.