Výsledky vyhledávání - "ZHANG, Chuanrui"

Report

TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers

Autor: Zhang, Chuanrui, Zou, Yingshuang, Li, Zhuoling, Yi, Minmin, Wang, Haoqian

Compared with previous 3D reconstruction methods like Nerf, recent Generalizable 3D Gaussian Splatting (G-3DGS) methods demonstrate impressive efficiency even in the sparse-view setting. However, the promising reconstruction performance of existing G

Externí odkaz: http://arxiv.org/abs/2408.13770

Zobrazit plný text záznamu

Report

Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images

Autor: Zhang, Chuanrui, Ling, Yonggen, Lu, Minglei, Qin, Minghan, Wang, Haoqian

We study the 3D object understanding task for manipulating everyday objects with different material properties (diffuse, specular, transparent and mixed). Existing monocular and RGB-D methods suffer from scale ambiguity due to missing or imprecise de

Externí odkaz: http://arxiv.org/abs/2407.06984

Zobrazit plný text záznamu

Report

VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection

Autor: Li, Zhuoling, Zhang, Chuanrui, Ma, Wei-Chiu, Zhou, Yipin, Huang, Linyan, Wang, Haoqian, Lim, SerNam, Zhao, Hengshuang

In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks. However, their performance in multi-view 3D object detection remains inferior to the state-of-the-art (SOTA) of convolutional neural

Externí odkaz: http://arxiv.org/abs/2304.01054

Zobrazit plný text záznamu

Report

Delving into the Pre-training Paradigm of Monocular 3D Object Detection

Autor: Li, Zhuoling, Zhang, Chuanrui, Yu, En, Wang, Haoqian

The labels of monocular 3D object detection (M3OD) are expensive to obtain. Meanwhile, there usually exists numerous unlabeled data in practical applications, and pre-training is an efficient way of exploiting the knowledge in unlabeled data. However

Externí odkaz: http://arxiv.org/abs/2206.03657

Zobrazit plný text záznamu