7 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…
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…
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…
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…
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…