UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair
Chuanrui Zhang*, Yingshuang Zou*, Zhengxian Wu, Yonggen Ling†✉, YuxiaoYang, Ziwei Wang✉
Website Paper Code

- We present UniPR, an end-to-end stereo framework that unifies 6D pose estimation and metric-scale 3D shape reconstruction, achieving up to 100× faster generation and 3× better shape-proportion accuracy for real-to-sim robotic manipulation.

LMGait: Language-Guided and Motion-Aware Gait Representation for Generalizable Recognition
Zhengxian Wu*, Chuanrui Zhang*, Shenao Jiang*, Hangrui Xu, Zirui Liao, Luyuan Zhang, Huaqiu Li, Peng Jiao, Haoqian Wang
Website Paper Code

- We present LMGait, a Language-Guided and Motion-Aware Gait Representation.

MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction
Yingshuang Zou*, Yikang Ding*, Chuantui Zhang, Xiaoyang Lyu, Feiyang Tan, Xiaojuan Qi, Haoqian Wang†
Website / Paper / Code

- We present MuDG, a controllable Multi-modal Diffusion model with Gaussian Splatting (GS) for Urban Scene Reconstruction.

TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers
Chuanrui Zhang*, Yingshuang Zou*, Zhuoling Li, Minmin Yi, Haoqian Wang†
Website Paper Code

- We present TranSplat, a transformer-based approach for generalizable 3D gaussian splatting from sparse multi-view images.

DAGait: Generalized Skeleton-Guided Data Alignment for Gait Recognition
Zhengxian Wu*, Chuanrui Zhang*, Hangrui Xu, Peng Jiao, Haoqian Wang
Website Paper Code

- We present DAGait, a universal data alignment strategy for gait recognition, to alleviate spatiotemporal distribution inconsistencies.

Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images
Chuanrui Zhang* , Yonggen Ling*†, Minglei Lu, Minghan Qin, Haoqian Wang†
Website Paper Code

- We present CODERS, a one-stage approach for Category-level Object Detection, pose Estimation and Reconstruction from Stereo images.

iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
Chuanrui Zhang, Zhengxian Wu, Guanxing Lu, Yansong Tang, Ziwei Wang
Website Paper Code Coming

- We present iMoWM, an interactive multi-modal world model for robotic manipulation.

VoxelFormer: Bird’s-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection
Zhuoling Li*, Chuanrui Zhang*, Wei-Chiu Ma, Yipin Zhou, Linyan Huang, Haoqian Wang†, SerNam Lim, Hengshuang Zhao†
Paper Code

- We introduce Dual-View Attention, a more effecient cross attention for Multi-view 3D Object Detection.