 |
Tianjia ShaoCollege of Computer Science and Technology address: Room 505 Mengminwei Building, Zijingang Campus, Zhejiang University, Hangzhou, 310058, China email: tjshao(AT)zju.edu.cn phone: (+86)0571-88206681-535 |
 |
News & Events
• I am looking for strongly-motivated PhD and Master students to join my research team. If you are interested in computer graphics and computer vision, please contact me.
• [July 2022] I served as the Technical Papers Committee member of ACM SIGGRAPH 2023 at Los Angeles, USA.
• [July 2021] I served as the Technical Papers Committee member of ACM SIGGRAPH 2022 at Vancouver, Canada.
• [May 2019] I served as the Program Co-Chair of Computational Visual Media 2022 at Beijing, China.
• [September 2020] I served as an associate editor for The Visual Computer.
• [August 2019] I left University of Leeds and joined Zhejiang University.
• [May 2018] I served as the Organizing Committee Co-Chair of Computational Visual Media 2019 at Bath, UK.
Research
My research focuses on the acquisition, reconstruction and generation of 3D contents in Computer Graphics and Computer Vision. My recent research includes 3D scene reconstruction (real-time dense SLAM, offline high-quality reconstruction, autonomous reconstruction with robots), digital human creation, and 3D AIGC.
Biography
Tianjia Shao is a ZJU100 Young Professor in the State Key Laboratory of CAD&CG, Zhejiang University. Previsouly He was a Lecturer in the School of Computing, University of Leeds, UK. He received his PhD in Computer Science from Institute for Advanced Study, Tsinghua University, under the guidance of Prof. Baining Guo, and his B.S. from the Department of Automation, Tsinghua University. During his PhD, he spent one year as a visiting researcher working with Prof. Niloy Mitra in University College London and four years as a research intern in Microsoft Research Asia. After that, he was an Assistant Researcher in the State Key Laboratory of CAD&CG, Zhejiang University.
Publications (grouped by year): 2025, 2024, 2023, 2022, Before 2022
2025
 |
High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model |
 |
Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs |
 |
EnliveningGS: Active Locomotion of 3DGS |
 |
Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering |
 |
GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation |
 |
Relightable Detailed Human Reconstruction from Sparse Flashlight Images |
 |
Animatable 3D Gaussians for modeling dynamic humans |
2024
 |
CPoser: An Optimization-after-Parsing Approach for Text-to-Pose Generation Using Large Language Models |
 |
RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting |
 |
X-SLAM: Scalable Dense SLAM for Task-aware Optimization using CSFD |
 |
3D Gaussian Blendshapes for Head Avatar Animation |
 |
Pattern Guided UV Recovery for Realistic Video Garment Texturing |
 |
Personalized Audio-Driven 3D Facial Animation via Style-Content Disentanglement |
 |
PIE-NeRF: Physics-Based Interactive Elastodynamics with NeRF |
 |
SynTalker: Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation |
 |
Understanding the vulnerability of skeleton-based Human Activity Recognition via black-box attack |
2023
 |
A Locality-Based Neural Solver for Optical Motion Capture |
 |
Adaptive Local Basis Functions for Shape Completion |
 |
Unsupervised image translation with distributional semantics awareness |
2022
 |
Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks |
 |
HoD-Net: High-Order Differentiable Deep Neural Networks and Applications |
 |
Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction |
Before 2022
 |
EyelashNet: A Dataset and A Baseline Method for Eyelash Matting |
 |
High-order Differentiable Autoencoder for Nonlinear Model Reduction |
 |
Unsupervised Image Generation with Infinite Generative Adversarial Networks |
 |
BASAR:Black-box Attack on Skeletal Action Recognition |
 |
Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack |
 |
Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation |
 |
One-shot Face Reenactment Using Appearance Adaptive Normalization |
 |
In-game Residential Home Planning via Visual Context-aware Global Relation Learning |
 |
EmbedMask: Embedding Coupling for Instance Segmentation |
 |
Mesh Guided One-shot Face Reenactment Using Graph Convolutional Networks |
 |
Dynamic Future Net: Diversified Human Motion Generation |
 |
Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks |
 |
Learning an Intrinsic Garment Space
for Interactive Authoring of Garment Animation |
 |
Accelerated Complex Step Finite Difference for Expedient Deformable Simulation |
 |
NNWarp: Neural Network-based Nonlinear Deformation |
 |
AutoSweep: Recovering 3D Editable Objects from a Single Photograph |
 |
Automatic Mechanism Modeling from a Single Image with CNNs |
 |
Warp-Guided GANs for Single-Photo Facial Animation |
 |
H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis |
 |
Efficient Voxelization Using Projected Optimal Scanline |
 |
Recovering Functional Mechanical Assemblies from Raw Scans |
 |
Dynamic Furniture Modeling Through Assembly Instructions |
 |
AutoHair: Fully Automatic Hair Modeling from A Single Image |
 |
Real-time Facial Animation with Image-based Dynamic Avatars |
 |
An Interactive Approach for Functional Prototype Recovery from a Single RGBD Image |
 |
Shape Completion from a Single RGBD Image |
 |
Imagining the Unseen: Stability-based Cuboid Arrangements for Scene Understanding |
 |
Interpreting Concept Sketches |
 |
An Interactive Approach to Semantic Modeling of Indoor Scenes with an RGBD Camera |
 |
Discriminative Sketch-based 3D Model Retrieval via Robust Shape Matching |
 |
Sampling-based Contact-rich Motion Control |