Dongqing Wang 王冬青

I am a PhD student at the Image and Visual Representation Lab, part of the School of Computer and Communication Sciences at EPFL, Switzerland. My PhD advisor is Prof. Sabine Süsstrunk. I'm currently working as a research scientist intern at Meta Reality Lab.

I received my Bachelor of Science degree in Computer Science with a minor in Music, as well as my Master of Engineering degree from Cornell University, where I was supervised by Prof. Steve Marschner.

Please feel free to reach out to me via email for research collaborations. For EPFL master's and bachelor's students interested in doing a semester project with me, a list of potential ideas can be found on our lab website.

GitHub  /  Google Scholar  /  LinkedIn

profile photo
News

Research

I'm interested in Computer Graphics, 3D Computer Vision and Machine Learning.

Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata
Dongqing Wang, Ehsan Pajouheshgar, Yitao Xu, Tong Zhang, Sabine Süsstrunk
CVPR Workshop (AI3DG) 2024
Poster

VNCA is a novel model for efficient volumetric style transfer that synthesizes multi-view consistent stylizing features on the target smoke in real-time, while exhibiting temporally coherent transitions between stylized frame.

InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields
Dongqing Wang, Tong Zhang, Alaa Abboud, Sabine Süsstrunk
CVPR, 2024
Project Page

InNeRF360 allows removing or editing of objects within an unbounded 360 degree NeRF through 2D image processing tools guided by 3D priors.

NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects
Dongqing Wang, Tong Zhang, Sabine Süsstrunk
ICCV 2023; ICCV 2023 TRICKY workshop Spotlight
Project Page

A neural representation for a 3D transparent object that disentangles its geometry and illumination-dependent appearance.

Selected School Projects

During my undergraduate studies at Cornell, I've been involved in many interesting projects from music visualization to on-skin interface development.

Interactive Renderer
CS 5625 Interactive Computer Graphics, 2021
Description

Implemented 1. a C++ based Ray Tracer and Rasterizer that include camera system, point, ambient and area light, etc. 2. a C++ based Rasterizer that implemented both forward and deferred shading, sun-sky model with bloom effect as well as ambient occlusion for light source.

Fractissimo: A Fractal Music Visualizer
CS 4621 Computer Graphics Practivum Final Project, 2019
Code

A fractal music visualizer that allows you to upload your favorite song (mp3, m4a, wav, aiff, or flac) and creates a bedazzling fractal visualization of the song for you.

Affective Robot Behaviour Generation by Multimodal Reinforcement Learning
CS 6670 Computer Vision Final Research Project, 2019
PDF

A multimodal Asynchronous Actor Critic Network to allow a low DOF robot to react to the received human emotional signals, e.g, happy, sad, fear and anger.

This work is based on Blossom: A Handcrafted Soft Social Robot developed in Professor Hoffman's Human-Robot Collaboration & Companionship Lab.

WovenSkin: Weaving Craft Techniques with On-Skin Technologies
Research Assist for Hybrid Body Lab, 2019
Project Page

Worked on the electronics and software control, detecting user gestures and hand movements as well as temperature changes of WovenSkin, a fabrication process to create customized functional devices that can be attached directly on human skin.

Visual Piano: A Tool to Visualize Tonal Music with Color
Cornell Make-a-thon, 2019
Project Page / YouTube

A device dedicated for everyone with or without a perfect hearing to create and enjoy music in various colorful ways.

Miscellaneous

More or less random stuff.

Confused bunny
cr. Steve Marschner, 2020

This image is based on a hand-drawn illustration showing an object with both viewing direction and light source by Professor Marschner in CS5625.

I found myself constantly confused during research, thus this image.


Kudos to Dr. Jon Barron for this website template.