collaborators

7 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…