Jun Xing (邢骏)


My research combines modern concepts in Computer Graphics, Human Computer Interaction and Machine Learning, with broad applications in digital painting, animation, visual effects, sculpting, image, and geometry analysis and synthesis, as well as UI/UX design. Now, I am moving my application platform to VR/AR! In particular, I am interested in analyzing the human-centered activities of authoring the various digital contents, and providing online “intelligent” suggestions, via a natural interface, to reduce manual labor while improving quality and performance.

I am now a postdoc at the Vision and Graphics group of Institute for Creative Technologies working with Prof. Hao Li. Prior to that, I got my PhD in CS from the University of Hong Kong, under the supervision of Prof. Li-Yi Wei, and my B.S. in Electronic Engineering and Information Science from University of Science and Technology of China (USTC), where my research was about Super-resolution of single image.

Find my CV and research statement.

Work Experience


Autocomplete 3D Sculpting

Mengqi Peng, Jun Xing, Li-Yi Wei

Accepted by SIGGRAPH 2018

[paper coming soon] [Media]


We propose an interactive 3D sculpting system that assists users in freely creating models without predefined scope.


Mesoscopic Facial Geometry Inference using Deep Neural Networks

Loc Huynh, Weikai Chen, Shunsuke Saito, Jun Xing, Koki Nagano, Andrew Jones, Hao Li, Paul Debevec

CVPR 2018 (Spotlight Presentation)

[paper coming soon]


We present a learning-based approach for synthesizing facial geometry at medium and fine scales from diffusely-lit facial texture maps.


Sequence-to-Sequence Learning via Shared Latent Representation

Xu Shen, Xinmei Tian, Jun Xing, Yong Rui, Dacheng Tao

AAAI 2018



We propose a star-like framework for general and flexible sequence-to-sequence learning, where different types of media contents (the peripheral nodes) could be encoded to and decoded from a shared latent representation (the central node).


Energy Brushes: Interactive Tools for Illustrating Stylized Elemental Dynamics

Jun Xing, Rubaiat Habib Kazi, Tovi Grossman, Li-Yi Wei, Jos Stam and George Fitzmaurice

UIST 2016

[paper] [Youtube] [presentation/slides]


We present a new animation framework and interactive system that enables artists to design elemental dynamics by sketching the underlying forces.


Autocomplete Hand-drawn Animations

Jun Xing, Li-Yi Wei, Takaaki Shiratori and Koji Yatani

SIGGRAPH Asia 2015

[paper] [Youtube] [Wired] [Fastcompany]


We present an interactive drawing system that helps users produce animation more easily and in a better quality while preserving manual drawing practices.


Autocomplete Painting Repetitions

Jun Xing, Hsiang-Ting Chen and Li-Yi Wei

SIGGRAPH Asia 2014

[paper] [Youtube]


We present an interactive digital painting system that autocompletes tedious repetitions while preserving nuanced variations and maintaining natural flows.

PhD Thesis

Autocomplete Hand-drawn Sketches and Animations

Jun Xing

University of Hong Kong



This thesis is basically a concatenation of my first three projects.