97 citations · 218 across the 12 of their papers we have counts for
10 papers · 1 filter
SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts
Yiding Sun, Zijie Xu, Hongqiang Lin +7
Multimodal 3D occupancy prediction underpins safe autonomous driving through comprehensive scene understanding. However, existing methods have largely pursued higher accuracy throu…
3D-TOGO: Towards Text-Guided Cross-Category 3D Object Generation
Zutao Jiang, Guansong Lu, Xiaodan Liang +4
Text-guided 3D object generation aims to generate 3D objects described by user-defined captions, which paves a flexible way to visualize what we imagined. Although some works have…
Frame-wise Cross-modal Matching for Video Moment Retrieval
Haoyu Tang, Jihua Zhu, Meng Liu +2
Video moment retrieval targets at retrieving a moment in a video for a given language query. The challenges of this task include 1) the requirement of localizing the relevant momen…
Robust Motion Averaging under Maximum Correntropy Criterion
Jihua Zhu, Jie Hu, Huimin Lu +2
Recently, the motion averaging method has been introduced as an effective means to solve the multi-view registration problem. This method aims to recover global motions from a set…
Registration of multi-view point sets under the perspective of expectation-maximization
Jihua Zhu, Jing Zhang, Huimin Lu +1
Registration of multi-view point sets is a prerequisite for 3D model reconstruction. To solve this problem, most of previous approaches either partially explore available informati…
Visual Space Optimization for Zero-shot Learning
Xinsheng Wang, Shanmin Pang, Jihua Zhu +3
Zero-shot learning, which aims to recognize new categories that are not included in the training set, has gained popularity owing to its potential ability in the real-word applicat…
K-means clustering for efficient and robust registration of multi-view point sets
Zutao Jiang, Jihua Zhu, Georgios D. Evangelidis +3
Generally, there are three main factors that determine the practical usability of registration, i.e., accuracy, robustness, and efficiency. In real-time applications, efficiency an…
Multi-view Registration Based on Weighted Low Rank and Sparse Matrix Decomposition of Motions
Congcong Jin, Jihua Zhu, Yaochen Li +3
Recently, the low rank and sparse (LRS) matrix decomposition has been introduced as an effective mean to solve the multi-view registration. It views each available relative motion…
Effective scaling registration approach by imposing the emphasis on the scale factor
Minmin Xu, Siyu Xu, Jihua Zhu +3
This paper proposes an effective approach for the scaling registration of -D point sets. Different from the rigid transformation, the scaling registration can not be formulated…
Weighted Motion Averaging for the Registration of Multi-View Range Scans
Rui Guo, Jihua Zhu, Yaochen Li +3
Multi-view registration is a fundamental but challenging problem in 3D reconstruction and robot vision. Although the original motion averaging algorithm has been introduced as an e…