Eve Mingxiao Li

I was a master’s student in the Dynamic Graphics Project (DGP) lab of the University of Toronto, advised by Prof. Tovi Grossman and Dr. Maurício Sousa. During my master’s, I have worked with Prof. Takeo Igarashi, Prof. Christian Sandor and Dr. Anran Qi at the University of Tokyo. Before joining DGP, I completed my Bachelor’s degree in Computer Science at the University of Waterloo with the co-op program.

Contact:

📧 eveli@dgp.toronto.edu

Publications

PerfectFit: Custom-Fit Garment Design in Augmented Reality

Akihiro Kiuchi, Anran Qi, Eve Mingxiao Li, Dávid Maruscsák, Christian Sandor, and Takeo Igarashi

In SIGGRAPH Asia 2023 XR , Sydney, NSW, Australia, 2023

Awareded Abs PDF Video Website

Best XR Demo Award

The mass production of the garment under a standard size in the garment industry does not consider individual body shape differences, resulting in unfitted garments and severe overproduction. Unluckily, the traditional tailor-fitting process is time-consuming, labour-intensive and expensive. We present PerfectFit, an interactive AR garment design system for fitting garments based on individual body shapes. Our system simulates the virtual garment reacting realistically to the client’s body shape and motion, and displays stereoscopic images to the designer via the AR glass. This enables the designer to identify the garment fitting via the client’s real-time motion from any viewpoint. Additionally, our system provides an editing interface to the designer which allows he/she interactively explores the design space of the garment and adjusts the fitting. Our system then reflects the changes on the client’s body. For the exhibit, visitors will play the role of the designer and interact with a person who plays the role of the client. The visitor designer role wears the AR Glass and can view the garment fitting issue on the client’s body. The visitor can explore the garment design space freely, and the author will provide slight guidance to the visitor on where and how to edit the garment to achieve better fits when needed. Our system will give the visitor an immersive experience of customizing the garment like a tailor.
EnchantedBrush: Animating in Mixed Reality for Storytelling and Communication

Eve Mingxiao Li, Anran Qi, Mauricio Sousa, and Tovi Grossman

In Graphics Interface , Victoria, British Columbia, Canada, 2023

Abs PDF Video

Recent progress in head-worn 3D displays has made mixed-reality storytelling, which allows digital art to interact with the physical surroundings, a new and promising medium to visualize ideas and bring sketches to life. While previous works have introduced dynamic sketching and animation in 3D spaces, visual and audio effects typically need to be manually specified. We present EnchantedBrush, a novel mixed-reality approach for creating animated storyboards with automatic motion and sound effects in real-world environments. People can create animations that interact with their physical surroundings using a set of interactive motion and sound brushes. We evaluated our approach with 12 participants, including professional artists. The results suggest that EnchantedBrush facilitates storytelling and communication, and utilizing the physical environment eases animation authoring and simplifies story creation.
A Drone Video Clip Dataset and its Applications in Automated Cinematography

Amirsaman Ashtari, Raehyuk Jung, Mingxiao Li, and Junyong Noh

In Pacific Graphics , Kyoto, Japan, 2022

Abs PDF

Drones became popular video capturing tools. Drone videos in the wild are first captured and then edited by humans to contain aesthetically pleasing camera motions and scenes. Therefore, edited drone videos have extremely useful information for cinematography and for applications such as camera path planning to capture aesthetically pleasing shots. To design intelligent camera path planners, learning drone camera motions from these edited videos is essential. However, first, this requires to filter drone clips and extract their camera motions out of these edited videos that commonly contain both drone and non-drone content. Moreover, existing video search engines return the whole edited video as a semantic search result and cannot return only drone clips inside an edited video. To address this problem, we proposed the first approach that can automatically retrieve drone clips from an unlabeled video collection using high-level search queries, such as ”drone clips captured outdoor in daytime from rural places". The retrieved clips also contain camera motions, camera view, and 3D reconstruction of a scene that can help develop intelligent camera path planners. To train our approach, we needed numerous examples of edited drone videos. To this end, we introduced the first large-scale dataset composed of edited drone videos. This dataset is also used for training and validating our drone video filtering algorithm. Both quantitative and qualitative evaluations have confirmed the validity of our method.

Relevant Experience

2023.10 - Present

Toronto, Canada
Software Engineer

Veeva Systems
- Developed a case management platform in React, JavaScript, CSS, and Java for both UI and backend functionalities, collaborating closely with Product Manager to align features with business goals
- Led the technical design and development of new features, coordinating efforts across developers, architects, and UX teams
2022.09 - 2023.03

Tokyo, Japan
Visiting Graduate Researcher

The University of Tokyo
- Designed an interactive prototype for garment design in Unity3D and C# using Canon AR HMD and Kinect Body Tracking that formed the basis for a publication, supervised by Prof. Takeo Igarashi and Prof. Christian Sandor
- Implemented an airflow visualization tool in Unity3D and C# with Canon AR HMD and fluid simulation software EmberGen
- Enhanced expertise in user interaction design and the integration of software and hardware development
2021.09 - 2023.08

Toronto, Canada
Graduate Student Researcher

University of Toronto
- Led a Mixed-Reality sketching project supervised by Prof. Tovi Grossman and Dr. Maurício Sousa
- Designed and implemented an interactive sketch-based system for communication and storytelling using Unity3D, C#, Oculus Quest 2, Zed Mini, and sketch recognition neural network in Python
- Developed a mixed-initiative interaction paradigm for visual and audio design, and conducted an exploratory user study with both general users and professional artists
2021.01 - 2021.04

Ottawa, Canada
Backend Developer Intern

IBM Canada
- Increased data streaming speeds by 30% by establishing multiple event ports and reducing lock contention
- Improved the performance of a customized Kafka connector by implementing Java concurrency
- Consolidated new features of Red Hat OpenShift Operators written in Golang by enabling new namespace creation, deploying operators, installing Custom Resources Definition (CRD) on clusters and investigating validating webhook configuration
2020.09 - 2020.12

Waterloo, Canada
Undergraduate Research Assistant

University of Waterloo
- Implemented physics-based animation projects in OpenGL, C++ and Processing which was supervised by Prof. Toshiya Hachisuka
- Built research knowledge in deformable object simulation with the approach of particle systems, mean curvature normal, volume preservation, triangle meshes and numerical methods
2019.09 - 2019.12

Cambridge, UK
Software Engineer Intern – AI/ML, Core Siri Infrastructure

Apple
- Strengthened fault identification in Siri verification by implementing features and functionalities in Java using instance-based learning techniques for a Siri verification service with a command-line interface
- Persisted results of instance-based learning by communication between clients and servers using Spring Boot framework, wrote a database manager using PostgreSQL, Hibernate ORM framework and jOOQ
- Enhanced the service performance efficiency of data processing by applying multithreading techniques
2019.01 - 2019.04

Daejeon, South Korea
Research Assistant - Visual Computing & Artificial Intelligence Lab

Korea Advanced Institute of Science and Technology (KAIST)
- Researched on drone videos and their applications under the supervision of Prof. Jean-Charles Bazin
- Developed deep learning techniques by training 2D/(2+1)D Convolutional Neural Networks (CNNs) on the classification of drone video categories using Keras and Python and achieved an accuracy rate of 80%
- Performed baseline evaluations of video cut detection, implemented heuristic algorithm in Python and analyzed camera motion path and 3D reconstruction using PhotoScan and Slam software
2018.05 - 2018.08

Toronto, Canada
Software Developer Intern

Ontario Institute for Cancer Research (OICR)
- Wrote a new module in Python and JavaScript for an open-source bioinformatics software MultiQC, and added new features and enhancements to modules which facilitated data analysis and research
- Advanced a data processing workflow using Java, which upgraded the existing applications and improved the overall efficiency of data analysis and file parsing procedures
- Provided users with easy access to the latest MultiQC reports by creating a report listing webpage using HTML, CSS, and JQuery
2017.09 - 2017.12

Toronto, Canada
QA Developer Intern

AudienceView
- Developed automated testing skills by writing testing suites in Node.js, leveraging WebDriver IO as an interface to test and ensure the quality of web applications
- Enhanced collaborative skills and leadership by working closely with team members to align testing strategies and managing a master testing branch in GitHub

Publications

Relevant Experience

Software Engineer

Veeva Systems

Visiting Graduate Researcher

The University of Tokyo

Graduate Student Researcher

University of Toronto

Backend Developer Intern

IBM Canada

Undergraduate Research Assistant

University of Waterloo

Software Engineer Intern – AI/ML, Core Siri Infrastructure

Apple

Research Assistant - Visual Computing & Artificial Intelligence Lab

Korea Advanced Institute of Science and Technology (KAIST)

Software Developer Intern

Ontario Institute for Cancer Research (OICR)

QA Developer Intern

AudienceView