53 citations · 193 across the 22 of their papers we have counts for
22 papers
As-Rigid-As-Possible Deformation of Gaussian Radiance Fields
Xinhao Tong, Tianjia Shao, Yanlin Weng +2
3D Gaussian Splatting (3DGS) models radiance fields as sparsely distributed 3D Gaussians, providing a compelling solution to novel view synthesis at high resolutions and real-time…
GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling
Yixuan Lai, Tianjia Shao, Weijia Dou +2
Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, causing entities that reappear a…
High-Fidelity Mobile Avatars with Pruned Local Blendshapes
Youyi Zhan, He Wang, Tianjia Shao +1
We propose a method to reconstruct high-fidelity human avatars from multi-view video that can run on mobile devices. Many works can model high-quality Gaussian-based full-body avat…
Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding
Yixuan Lai, He Wang, Kun Zhou +1
Human identity-preserving text-to-video generation remains challenging under large changes in viewpoint, facial expression, illumination, and motion. Existing methods condition the…
Gaussian-Plus-SDF SLAM: High-fidelity 3D Reconstruction at 150+ fps
Zhexi Peng, Kun Zhou, Tianjia Shao
While recent Gaussian-based SLAM methods achieve photorealistic reconstruction from RGB-D data, their computational performance remains a critical bottleneck. State-of-the-art tech…
Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs
Youyi Zhan, Tianjia Shao, Yin Yang +1
Many works have succeeded in reconstructing Gaussian human avatars from multi-view videos. However, they either struggle to capture pose-dependent appearance details with a single…
High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model
Yiyang Shen, Kun Zhou, He Wang +2
Recently single-view 3D generation via Gaussian splatting has emerged and developed quickly. They learn 3D Gaussians from 2D RGB images generated from pre-trained multi-view diffus…
Pattern Guided UV Recovery for Realistic Video Garment Texturing
Youyi Zhan, Tuanfeng Y. Wang, Tianjia Shao +1
The fast growth of E-Commerce creates a global market worth USD 821 billion for online fashion shopping. What unique about fashion presentation is that, the same design can usually…
Interactive Rendering of Relightable and Animatable Gaussian Avatars
Youyi Zhan, Tianjia Shao, He Wang +2
Creating relightable and animatable avatars from multi-view or monocular videos is a challenging task for digital human creation and virtual reality applications. Previous methods…
Elastic Locomotion with Mixed Second-order Differentiation
Siyuan Shen, Tianjia Shao, Kun Zhou +4
We present a framework of elastic locomotion, which allows users to enliven an elastic body to produce interesting locomotion by prescribing its high-level kinematics. We formulate…
RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting
Zhexi Peng, Tianjia Shao, Yong Liu +4
We present Real-time Gaussian SLAM (RTG-SLAM), a real-time 3D reconstruction system with an RGBD camera for large-scale environments using Gaussian splatting. The system features a…
X-SLAM: Scalable Dense SLAM for Task-aware Optimization using CSFD
Zhexi Peng, Yin Yang, Tianjia Shao +2
We present X-SLAM, a real-time dense differentiable SLAM system that leverages the complex-step finite difference (CSFD) method for efficient calculation of numerical derivatives,…
3D Gaussian Blendshapes for Head Avatar Animation
Shengjie Ma, Yanlin Weng, Tianjia Shao +1
We introduce 3D Gaussian blendshapes for modeling photorealistic head avatars. Taking a monocular video as input, we learn a base head model of neutral expression, along with a gro…
A Locality-based Neural Solver for Optical Motion Capture
Xiaoyu Pan, Bowen Zheng, Xinwei Jiang +8
We present a novel locality-based learning method for cleaning and solving optical motion capture data. Given noisy marker data, we propose a new heterogeneous graph neural network…
Adaptive Local Basis Functions for Shape Completion
Hui Ying, Tianjia Shao, He Wang +2
In this paper, we focus on the task of 3D shape completion from partial point clouds using deep implicit functions. Existing methods seek to use voxelized basis functions or the on…
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
Yunfeng Diao, He Wang, Tianjia Shao +4
Human Activity Recognition (HAR) has been employed in a wide range of applications, e.g. self-driving cars, where safety and lives are at stake. Recently, the robustness of skeleto…
Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks
Xiaoyu Pan, Jiaming Mai, Xinwei Jiang +6
We present a learning algorithm that uses bone-driven motion networks to predict the deformation of loose-fitting garment meshes at interactive rates. Given a garment, we generate…
Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction
Jiawei Lu, He Wang, Tianjia Shao +2
Generating new images with desired properties (e.g. new view/poses) from source images has been enthusiastically pursued recently, due to its wide range of potential applications.…
Unsupervised Image Generation with Infinite Generative Adversarial Networks
Hui Ying, He Wang, Tianjia Shao +2
Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little superv…
High-order Differentiable Autoencoder for Nonlinear Model Reduction
Siyuan Shen, Yang Yin, Tianjia Shao +4
This paper provides a new avenue for exploiting deep neural networks to improve physics-based simulation. Specifically, we integrate the classic Lagrangian mechanics with a deep au…
SMART: Skeletal Motion Action Recognition aTtack
He Wang, Feixiang He, Zhexi Peng +4
Adversarial attack has inspired great interest in computer vision, by showing that classification-based solutions are prone to imperceptible attack in many tasks. In this paper, we…
DeepWarp: DNN-based Nonlinear Deformation
Ran Luo, Tianjia Shao, Huamin Wang +3
DeepWarp is an efficient and highly re-usable deep neural network (DNN) based nonlinear deformable simulation framework. Unlike other deep learning applications such as image recog…