Jingwei Huang

Ph.D Student

Geometric Computing Lab
Dept. of Computer Science
Stanford University, USA

Office: Gates 387
Address: 353 Serra Mall, Stanford, CA 94305
Email: jingweih@stanford.edu

bio / google scholar / publication

Research Statement

My research interests are computer graphics, computer vision, virtual reality and geometry processing. After involving in projects from different areas in graphics and vision, I determined to focus on RGB-D SLAM and Real-time reconstruction in order to produce read-to-use high-quality scanning geometry. My ultimate goal is to effectively recognize the scanning data in a higher level.

Towards the goal, I believe that it is essential to bridge two fields --- computer vision and computer graphics, where the former focuses on visual SLAM and the latter on geometrical data analysis and synthesis.

To achieve the goal of producing high-quality geometry, we need high-quality texture and clean geometry. I contributed to the 3D geometry texture synthesis component of the "unsupervised texture synthesis" project. Now, I am upgrading the "bundle-fusion scanning system to get clean geometry with good planar abstraction.

Skills

Proficient with C/C++ Programming

Good at Matlab/CUDA/GLSL/HLSL GPU Programming

Familiar with Python/Java/C# Programming

Familiar with PHP/Javascript/Unity/Android programming

My Mission

To my knowledge, there are creative ideas and awesome applications emerging every year, and the demos are very fancy. However, most of these potential applications can hardly be used in common days, mostly due to the problem of robustness in graphics or poor accuracy in vision. I view my mission as to solve problems in computer graphics and vision, particularly in environment reconstruction from images and video.

My first trial was a start-up building stereo panorama video stitching system. I was the CTO and co-founder of the company, developing a similar system with Google Jump (at that time, Jump is not publicly known yet). Finally, the company ended by being purchased. I view the start-up as not a success because we never solved the problem robustly. The problem is that only 2D information is not enough for perfect stitching (inconsistency at the image boundary).

Currently, I am trying to use RGB-D SLAM to get complete 3D environment information. Unfortunately, I noticed that camera distortion, depth noises, and inaccurate pair-wise image matching makes camera poses always not accurate enough for good reconstruction. Rolling shutter camera and wrong camera poses cause blurred and inconsistent texture, respectively. Since current system can get a good global structure, I hope to use texture and geometry analysis to fix the problems and produce ready-to-use reconstructions.

Publications

Computer Vision and Computer Graphics

3DLite: Towards Commodity 3D Scanning for Content Creation
Jingwei Huang, Angela Dai, Leonidas Guibas, Matthias Niessner
SIGGRAPH Asia, 2017
Complete the geometry and color of 3D scanning model. Detect planar structure of the geometry, extrapolate to complete the scene. Texture optimization by fixing misalignment, motion blur and auto-exposure artifacts.
6-DOF VR Videos with a Single 360-Camera
Jingwei Huang, Zhili Chen, Duygu Ceylan, Hailin Jin
IEEE VR, 2017
Build a VR application that offer 6-DOF freedom with translation and rotation with input as a monoscopic 360 video.
Unsupervised Texture Transfer from Images to Model Collections
Tuanfeng Y. Wang, Hao Su, Qixing Huang, Jingwei Huang, Leonidas Guibas, Niloy J. Mitra
SIGGRAPH Asia, 2016
Transfer textures from product images to 3D shapes. The increased texture variation in ShapeNet is validated to be effective for RenderForCNN. The technique can future be used in improving texture of scanning data.
Real-time Interactive Tree Animation
Ed Quigley, Yue Yu, Jingwei Huang, Winnie Lin, Rod Fedkiw
IEEE TVCG, 2017
Posing and Animating botanical tree models interactively in real time. We use an articulated rigid body model with as-stiff-as-desired rotational springs in conjunction with our newly proposed simulation technique.
Automatic Thumbnail Generation Based on Visual Representativeness and Foreground Recognizability
Jingwei Huang, Huarong Chen, Bin Wang, Stephen Lin
ICCV, 2015
Generating image thumbnail balancing between visual representativeness and foreground recognizability. We propose a combination of various features and use SVM model to learn good thumbnail.
A Surface Estimation Method for Space-time Correspondences
Jingwei Huang, Bin Wang, Pradeep Sen, Wenping Wang
IEEE Transactions on Image Processing, 2015
Using B-Spline Approximation and Extension method to refine dense non-rigid correspondences in images or video.

Other Selected Projects

Real-time RGB-D SLAM and 3D Reconstruction
Jingwei Huang, Matthias Niesser, Leonidas Guibas
In progress
We use plane matching, structural information together with SIFT feature to do real-time RGBD SLAM. The system can get globally consistent structure in a large space with a long scan. Currently, I am trying to use planes to abstract the scenes, and using texture synthesis to achieve a ready-to-use 3D reconstruction.
Stereo Panorama Stitching with 14 GOPROs
Jingwei Huang
Qingxian Tech.
This is what I do as a startup during 3/2015 and 8/2015. The company was purchased by Wei-Shi-Zai-Xian in 3/2016.
PhysBowling: Real-Time Interactive Simulation of Rigid Bodies
Jingwei Huang, Bin Wang
GPU Acceleration of Incompressible Smoothed Particle Hydrodynamics and Applications
Jingwei Huang, Yun Fei, Bin Wang
GPU Acceleration of Incompressible Smoothed Particle Hydrodynamics and Applications
Jingwei Huang, Yun Fei, Bin Wang

Working Experience