10 citations · 23 across the 16 of their papers we have counts for
16 papers
InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding
Minchao Jiang, Xiaoxuan Ma, Shunyu Jia +3
Feed-forward 3D Gaussian Splatting (3DGS) enables efficient and generalizable 3D reconstruction, but current feed-forward 3DGS methods for scene understanding remain largely catego…
Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality
Yuan Xu, Zimu Zhang, Xiaoxuan Ma +3
Virtual and augmented reality systems increasingly demand intelligent adaptation to user behaviors for enhanced interaction experiences. Achieving this requires accurately understa…
RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image Generation
Lexi Pang, Liheng Zhang, Hang Ye +2
Text-to-image (T2I) diffusion models have shown remarkable success in generating high-quality images from text prompts. Recent efforts extend these models to incorporate conditiona…
Electromagnetic Inverse Scattering from a Single Transmitter
Yizhe Cheng, Chunxun Tian, Haoru Wang +3
Electromagnetic Inverse Scattering Problems (EISP) seek to reconstruct relative permittivity from scattered fields and are fundamental to applications like medical imaging. This in…
FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling
Hang Ye, Xiaoxuan Ma, Hai Ci +2
Achieving realistic animated human avatars requires accurate modeling of pose-dependent clothing deformations. Existing learning-based methods heavily rely on the Linear Blend Skin…
SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens
Chi Su, Xiaoxuan Ma, Jiajun Su +1
We propose a one-stage framework for real-time multi-person 3D human mesh estimation from a single RGB image. While current one-stage methods, which follow a DETR-style pipeline, a…
Efficient Action Counting with Dynamic Queries
Xiaoxuan Ma, Zishi Li, Qiuyan Shang +4
Temporal repetition counting aims to quantify the repeated action cycles within a video. The majority of existing methods rely on the similarity correlation matrix to characterize…
Real-time Holistic Robot Pose Estimation with Unknown States
Shikun Ban, Juling Fan, Xiaoxuan Ma +3
Estimating robot pose from RGB images is a crucial problem in computer vision and robotics. While previous methods have achieved promising performance, most of them presume full kn…
Social Motion Prediction with Cognitive Hierarchies
Wentao Zhu, Jason Qin, Yuke Lou +4
Humans exhibit a remarkable capacity for anticipating the actions of others and planning their own actions accordingly. In this study, we strive to replicate this ability by addres…
ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
Xiaoxuan Ma, Stephan P. Kaufhold, Jiajun Su +6
Understanding the behavior of non-human primates is crucial for improving animal welfare, modeling social behavior, and gaining insights into distinctively human and phylogenetical…
Human Motion Generation: A Survey
Wentao Zhu, Xiaoxuan Ma, Dongwoo Ro +6
Human motion generation aims to generate natural human pose sequences and shows immense potential for real-world applications. Substantial progress has been made recently in motion…
3D Human Mesh Estimation from Virtual Markers
Xiaoxuan Ma, Jiajun Su, Chunyu Wang +2
Inspired by the success of volumetric 3D pose estimation, some recent human mesh estimators propose to estimate 3D skeletons as intermediate representations, from which, the dense…
GFPose: Learning 3D Human Pose Prior with Gradient Fields
Hai Ci, Mingdong Wu, Wentao Zhu +4
Learning 3D human pose prior is essential to human-centered AI. Here, we present GFPose, a versatile framework to model plausible 3D human poses for various applications. At the co…
MotionBERT: A Unified Perspective on Learning Human Motion Representations
Wentao Zhu, Xiaoxuan Ma, Zhaoyang Liu +3
We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. Specifica…
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
Jiajun Su, Chunyu Wang, Xiaoxuan Ma +2
While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform…
Context Modeling in 3D Human Pose Estimation: A Unified Perspective
Xiaoxuan Ma, Jiajun Su, Chunyu Wang +2
Estimating 3D human pose from a single image suffers from severe ambiguity since multiple 3D joint configurations may have the same 2D projection. The state-of-the-art methods ofte…