Autonomous Character-Scene Interaction Synthesis from Text Instruction

no code implementations • 4 Oct 2024 • Nan Jiang, Zimo He, Zi Wang, Hongjie Li, Yixin Chen, Siyuan Huang, Yixin Zhu

Synthesizing human motions in 3D environments, particularly those with complex activities such as locomotion, hand-reaching, and human-object interaction, presents substantial demands for user-defined waypoints and stage transitions.

Human-Object Interaction Detection

Scaling Up Dynamic Human-Scene Interaction Modeling

no code implementations • CVPR 2024 • Nan Jiang, Zhiyuan Zhang, Hongjie Li, Xiaoxuan Ma, Zan Wang, Yixin Chen, Tengyu Liu, Yixin Zhu, Siyuan Huang

Confronting the challenges of data scarcity and advanced motion synthesis in human-scene interaction modeling, we introduce the TRUMANS dataset alongside a novel HSI motion synthesis method.

Motion Synthesis

Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo

1 code implementation • 26 Dec 2023 • Hongjie Li, Yao Guo, Xianwei Zheng, Hanjiang Xiong

This paper introduces a learnable Deformable Hypothesis Sampler (DeformSampler) to address the challenging issue of noisy depth estimation for accurate PatchMatch Multi-View Stereo (MVS).

Depth Estimation Depth Prediction

Topic-Based Chinese Message Sentiment Analysis: A Multilayered Analysis System

no code implementations • WS 2015 • Hongjie Li, Zhongqian Sun, Wei Yang

Emotion Recognition Sentiment Analysis