Search Results for author: Tianjia Shao

Found 27 papers, 11 papers with code

ElastoGen: 4D Generative Elastodynamics

no code implementations23 May 2024 Yutao Feng, Yintong Shang, Xiang Feng, Lei Lan, Shandian Zhe, Tianjia Shao, Hongzhi Wu, Kun Zhou, Hao Su, Chenfanfu Jiang, Yin Yang

We present ElastoGen, a knowledge-driven model that generates physically accurate and coherent 4D elastodynamics.

3D Gaussian Blendshapes for Head Avatar Animation

no code implementations30 Apr 2024 Shengjie Ma, Yanlin Weng, Tianjia Shao, Kun Zhou

We introduce 3D Gaussian blendshapes for modeling photorealistic head avatars.

RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting

no code implementations30 Apr 2024 Zhexi Peng, Tianjia Shao, Yong liu, Jingke Zhou, Yin Yang, Jingdong Wang, Kun Zhou

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.

3D Reconstruction Novel View Synthesis

Gaussian Splashing: Dynamic Fluid Synthesis with Gaussian Splatting

no code implementations27 Jan 2024 Yutao Feng, Xiang Feng, Yintong Shang, Ying Jiang, Chang Yu, Zeshun Zong, Tianjia Shao, Hongzhi Wu, Kun Zhou, Chenfanfu Jiang, Yin Yang

We demonstrate the feasibility of integrating physics-based animations of solids and fluids with 3D Gaussian Splatting (3DGS) to create novel effects in virtual scenes reconstructed using 3DGS.

PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF

no code implementations CVPR 2024 Yutao Feng, Yintong Shang, Xuan Li, Tianjia Shao, Chenfanfu Jiang, Yin Yang

We show that physics-based simulations can be seamlessly integrated with NeRF to generate high-quality elastodynamics of real-world objects.

Animatable 3D Gaussians for High-fidelity Synthesis of Human Motions

no code implementations22 Nov 2023 Keyang Ye, Tianjia Shao, Kun Zhou

The learnable code serves as a pose-dependent appearance embedding for refining the erroneous appearance caused by geometric transformation of Gaussians, based on which an appearance refinement model is learned to produce residual Gaussian properties to match the appearance in target pose.

A Locality-based Neural Solver for Optical Motion Capture

1 code implementation1 Sep 2023 Xiaoyu Pan, Bowen Zheng, Xinwei Jiang, Guanglong Xu, Xianli Gu, Jingxiang Li, Qilong Kou, He Wang, Tianjia Shao, Kun Zhou, Xiaogang Jin

Finally, we propose a training regime based on representation learning and data augmentation, by training the model on data with masking.

Data Augmentation Graph Neural Network +1

Adaptive Local Basis Functions for Shape Completion

1 code implementation17 Jul 2023 Hui Ying, Tianjia Shao, He Wang, Yin Yang, Kun Zhou

Quantitative and qualitative experiments demonstrate that our method outperforms the state-of-the-art methods in shape completion, detail preservation, generalization to unseen geometries, and computational cost.

Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack

4 code implementations21 Nov 2022 Yunfeng Diao, He Wang, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg, Meng Wang

Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.

Adversarial Attack Human Activity Recognition +2

Predicting Loose-Fitting Garment Deformations Using Bone-Driven Motion Networks

1 code implementation3 May 2022 Xiaoyu Pan, Jiaming Mai, Xinwei Jiang, Dongxue Tang, Jingxiang Li, Tianjia Shao, Kun Zhou, Xiaogang Jin, Dinesh Manocha

We present a learning algorithm that uses bone-driven motion networks to predict the deformation of loose-fitting garment meshes at interactive rates.

Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction

no code implementations2 Feb 2022 Jiawei Lu, He Wang, Tianjia Shao, Yin Yang, Kun Zhou

However, as source images are often misaligned due to the large disparities among the camera settings, strong assumptions have been made in the past with respect to the camera(s) or/and the object in interest, limiting the application of such techniques.

Pose-Guided Image Generation

Unsupervised Image Generation with Infinite Generative Adversarial Networks

1 code implementation ICCV 2021 Hui Ying, He Wang, Tianjia Shao, Yin Yang, Kun Zhou

Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision.

Image Generation

Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack

1 code implementation CVPR 2021 He Wang, Feixiang He, Zhexi Peng, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg

In this paper, we examine the robustness of state-of-the-art action recognizers against adversarial attack, which has been rarely investigated so far.

Action Recognition Adversarial Attack +4

BASAR:Black-box Attack on Skeletal Action Recognition

1 code implementation CVPR 2021 Yunfeng Diao, Tianjia Shao, Yong-Liang Yang, Kun Zhou, He Wang

The robustness of skeleton-based activity recognizers has been questioned recently, which shows that they are vulnerable to adversarial attacks when the full-knowledge of the recognizer is accessible to the attacker.

Action Recognition Adversarial Attack +1

High-order Differentiable Autoencoder for Nonlinear Model Reduction

no code implementations19 Feb 2021 Siyuan Shen, Yang Yin, Tianjia Shao, He Wang, Chenfanfu Jiang, Lei Lan, Kun Zhou

This paper provides a new avenue for exploiting deep neural networks to improve physics-based simulation.

Vocal Bursts Intensity Prediction

In-game Residential Home Planning via Visual Context-aware Global Relation Learning

no code implementations8 Feb 2021 Lijuan Liu, Yin Yang, Yi Yuan, Tianjia Shao, He Wang, Kun Zhou

In this paper, we propose an effective global relation learning algorithm to recommend an appropriate location of a building unit for in-game customization of residential home complex.

Graph Generation Relation

One-shot Face Reenactment Using Appearance Adaptive Normalization

no code implementations8 Feb 2021 Guangming Yao, Yi Yuan, Tianjia Shao, Shuang Li, Shanqi Liu, Yong liu, Mengmeng Wang, Kun Zhou

The paper proposes a novel generative adversarial network for one-shot face reenactment, which can animate a single face image to a different pose-and-expression (provided by a driving image) while keeping its original appearance.

Face Reenactment Generative Adversarial Network

Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation

no code implementations5 Feb 2021 Jilin Tang, Yi Yuan, Tianjia Shao, Yong liu, Mengmeng Wang, Kun Zhou

In this paper we tackle the problem of pose guided person image generation, which aims to transfer a person image from the source pose to a novel target pose while maintaining the source appearance.

Image Generation

Second-order Neural Network Training Using Complex-step Directional Derivative

no code implementations15 Sep 2020 Siyuan Shen, Tianjia Shao, Kun Zhou, Chenfanfu Jiang, Feng Luo, Yin Yang

We believe our method will inspire a wide-range of new algorithms for deep learning and numerical optimization.

Second-order methods

Dynamic Future Net: Diversified Human Motion Generation

no code implementations25 Aug 2020 Wenheng Chen, He Wang, Yi Yuan, Tianjia Shao, Kun Zhou

We evaluate our model on a wide range of motions and compare it with the state-of-the-art methods.

Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks

no code implementations18 Aug 2020 Guangming Yao, Yi Yuan, Tianjia Shao, Kun Zhou

In this paper, we introduce a method for one-shot face reenactment, which uses the reconstructed 3D meshes (i. e., the source mesh and driving mesh) as guidance to learn the optical flow needed for the reenacted face synthesis.

Decoder Face Generation +3

AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph

1 code implementation27 May 2020 Xin Chen, Yuwei Li, Xi Luo, Tianjia Shao, Jingyi Yu, Kun Zhou, Youyi Zheng

We base our work on the assumption that most human-made objects are constituted by parts and these parts can be well represented by generalized primitives.

3D Reconstruction Instance Segmentation +1

Unsupervised Facial Action Unit Intensity Estimation via Differentiable Optimization

no code implementations13 Apr 2020 Xinhui Song, Tianyang Shi, Tianjia Shao, Yi Yuan, Zunlei Feng, Changjie Fan

The generator learns to "render" a face image from a set of facial parameters in a differentiable way, and the feature extractor extracts deep features for measuring the similarity of the rendered image and input real image.

Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks

3 code implementations CVPR 2020 Jiangke Lin, Yi Yuan, Tianjia Shao, Kun Zhou

In this paper, we introduce a method to reconstruct 3D facial shapes with high-fidelity textures from single-view images in-the-wild, without the need to capture a large-scale face texture database.

3D Face Reconstruction

EmbedMask: Embedding Coupling for One-stage Instance Segmentation

3 code implementations4 Dec 2019 Hui Ying, Zhaojin Huang, Shu Liu, Tianjia Shao, Kun Zhou

The pixel-level clustering enables EmbedMask to generate high-resolution masks without missing details from repooling, and the existence of proposal embedding simplifies and strengthens the clustering procedure to achieve high speed with higher performance than segmentation-based methods.

Clustering Instance Segmentation +2

SMART: Skeletal Motion Action Recognition aTtack

no code implementations16 Nov 2019 He Wang, Feixiang He, Zhexi Peng, Yong-Liang Yang, Tianjia Shao, Kun Zhou, David Hogg

In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions.

Action Recognition Adversarial Attack +2

DeepWarp: DNN-based Nonlinear Deformation

1 code implementation24 Mar 2018 Ran Luo, Tianjia Shao, Huamin Wang, Weiwei Xu, Kun Zhou, Yin Yang

DeepWarp is an efficient and highly re-usable deep neural network (DNN) based nonlinear deformable simulation framework.


Cannot find the paper you are looking for? You can Submit a new open access paper.