Search Results for author: Tianyi Xie

Found 6 papers, 0 papers with code

Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication

no code implementations28 May 2024 Yunuo Chen, Tianyi Xie, Zeshun Zong, Xuan Li, Feng Gao, Yin Yang, Ying Nian Wu, Chenfanfu Jiang

Existing diffusion-based text-to-3D generation methods primarily focus on producing visually realistic shapes and appearances, often neglecting the physical constraints necessary for downstream tasks.

Sunnie: An Anthropomorphic LLM-Based Conversational Agent for Mental Well-Being Activity Recommendation

no code implementations22 May 2024 Siyi Wu, Feixue Han, Bingsheng Yao, Tianyi Xie, Xuan Zhao, Dakuo Wang

A longstanding challenge in mental well-being support is the reluctance of people to adopt psychologically beneficial activities, often due to a lack of motivation, low perceived trustworthiness, and limited personalization of recommendations.

GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details

no code implementations20 May 2024 Boqian Li, Xuan Li, Ying Jiang, Tianyi Xie, Feng Gao, Huamin Wang, Yin Yang, Chenfanfu Jiang

In this paper, we propose GarmentDreamer, a novel method that leverages 3D Gaussian Splatting (GS) as guidance to generate wearable, simulation-ready 3D garment meshes from text prompts.

Texture Synthesis

VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Reality

no code implementations30 Jan 2024 Ying Jiang, Chang Yu, Tianyi Xie, Xuan Li, Yutao Feng, Huamin Wang, Minchen Li, Henry Lau, Feng Gao, Yin Yang, Chenfanfu Jiang

As consumer Virtual Reality (VR) and Mixed Reality (MR) technologies gain momentum, there's a growing focus on the development of engagements with 3D virtual content.

Mixed Reality Semantic Segmentation

PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

no code implementations20 Nov 2023 Tianyi Xie, Zeshun Zong, Yuxing Qiu, Xuan Li, Yutao Feng, Yin Yang, Chenfanfu Jiang

We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis.

Motion Synthesis

Towards Realistic Visual Dubbing with Heterogeneous Sources

no code implementations17 Jan 2022 Tianyi Xie, Liucheng Liao, Cheng Bi, Benlai Tang, Xiang Yin, Jianfei Yang, Mingjie Wang, Jiali Yao, Yang Zhang, Zejun Ma

The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video.

Disentanglement Talking Head Generation

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