Yu-Shiang Wong

Ph.D. student at Smart Geometry Group, Unervisity College London (UCL).

My research interests include Neural representation, 3D/4D reconstruction, and developing interactive graphics systems.

Email:  yushiangwtw@gmail.com

RigidFusion: RGB-D Scene Reconstruction with Rigidly-moving Objects


[Project Website]
We introduce RigidFusion. A RGB-D reconstruction system targets on dynamic environments without using object priors. rigidfusion

Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences


[Project Website]
Multi-object tracking with deep priors using RGB-D input. Our key insight is geometry completion helps tracking. seebehindobjs2021

Meaning-based Statistical Math Word Problem Solver


A goal-oriented meaning-based statistical framework is presented to solve the math word problem. Our system is able to generate a reasonable explanation. img

SmartAnnotator: Annotating Indoor RGBD Images


[Project Website]
We present SMARTANNOTATOR, an interactive system to facilitate annotating raw RGBD images. The system performs the tedious tasks and iteratively refines users’ annotations.

Machine Learning Toolbox

This toolbox implements common machine learning methods in MATLAB, including support vector machine (SVM) with sequential minimal optimization, Laplacian SVM, spectral clustering.

3D Object Composition

In this project, we developed a system that support 3D object composition. It was integrated into Blender via Blender’s Python API to add special visual effects.
Youtube Video I - Object Compostion
Youtube Video II - VFX
cube1 API

Web-based Image Annotator

This is a web-based tool that allows users to annotate 2D images. We used this tools to collect over ninety annotations. This tool was further integrated to our single- view reconstruction system. light_anno_img

Software Renderer

This renderer employs fixed-function rendering pipeline and supports: triangle rasterization, textures sampling, mipmap, and bump mapping. fx_renderer_img