I am currently the chief scientist at Manycore Tech Inc.. From 2013 to 2021, I was a research associate and then an assistant professor in the College of Information Sciences and Technology at Penn State University. I completed my Ph.D in Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign in 2013. I was supervised by Prof. Yi Ma. I received my Bachelor Degree in Automation from Tsinghua University, China, and Master Degree in ECE from UIUC, respectively.
My research interest lies in the broad area of computer vision, machine learning, signal processing, and applied data sciences. I am particularly focusing on 3D Vision. Specifically, I develop novel computational tools to model and analyze the 3D environments from big visual data, and apply them to solve challenging real-world problems in computer-aided design, VR/AR, social media, and more.
NeRF-Enhanced Outpainting for Faithful Field-of-View Extrapolation |
|
PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs |
|
Two-stage Content-Aware Layout Generation for Poster Designs |
|
Deep Learning Assisted Optimization for 3D Reconstruction from Single 2D Line Drawings |
|
End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement |
|
Neural Face Identification in a 2D Wireframe Projection of a Manifold Object |
|
Deep Depth from Focus with Differential Focus Volume |
|
Iterative Design and Prototyping of Computer Vision Mediated Remote Sighted Assistance |
|
Towards Robust Human Trajectory Prediction in Raw Videos |
|
Neural Wireframe Renderer: Learning Wireframe to Image Translations |
|
Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling |
|
Data-driven Distributed State Estimation and Behavior Modeling in Sensor Networks |
|
Superpixel Segmentation with Fully Convolutional Networks |
|
Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embedding |
|
Recovering 3D Planes from a Single Image via Convolutional Neural Networks |
|
Learning to Parse Wireframes in Images of Man-Made Environments |
|
Discovering Triangles in Protraits for Supporting Photographic Creation |
|
Beyond Saliency: Assessing Visual Balance with High-Level Cues |
|
Detecting Dominant Vanishing Points In Natural Scenes with Application to Composition-Sensitive Image Retrieval |
|
Improving Offline Handwritten Chinese Character Recognition by Iterative Refinement |
|
Learning to Read Irregular Text with Attention Mechanisms |
|
Label Information Guided Graph Construction for Semi-Supervised Learning |
|
Smart Library: Identifying Books in a Library using Richly Supervised Deep Scene Text Reading |
|
Multi-scale FCN with Instance Aware Segmentation for Arbitrary Oriented Word Spotting In The Wild |
|
Robust Plane-based Calibration of Multiple Non-Overlapping Cameras |
|
Aggregating Local Context for Accurate Scene Text Detection |
|
Detecting Arbitrary Orientated Text in the Wild with a Visual Attention Model |
|
Modeling Perspective Effects in Photographic Composition |
|
Fast L1-Minimization Algorithms For Robust Face Recognition |
|
Plane-Based Content-Preserving Warps for Video Stabilization |
|
Single-Sample Face Recognition with Image Corruption and Misalignment via Sparse Illumination Transfer |
|
Robust Plane-Based Structure From Motion |
|
Towards a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation |
|
Holistic Reconstruction of Urban Structures from Low-rank Textures |
|
Towards a Robust Face Recognition System using Compressive Sensing |
|
Stable Principal Component Pursuit |
|
Face Recognition with Contiguous Occlusion using Markov Random Fields |
|
Towards a Practical Face Recognition System: Robust Registration and Illumination via Sparse Representation |
|
Separation of A Subspace-Sparse Signal: Algorithms and Conditions |
|
Nearest-Subspace Patch Matching for Face Recognition Under Varying Pose and Illumination |