Výsledky vyhledávání - "Gong, Haoran"

Report

CompetitorFormer: Competitor Transformer for 3D Instance Segmentation

Autor: Wang, Duanchu, Liu, Jing, Gong, Haoran, Quan, Yinghui, Wang, Di

Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification confidence and IoU scores to select the top prediction as the final ou

Externí odkaz: http://arxiv.org/abs/2411.14179

Zobrazit plný text záznamu

Report

Enhanced Semantic Segmentation for Large-Scale and Imbalanced Point Clouds

Autor: Gong, Haoran, Wang, Haodong, Wang, Di

Semantic segmentation of large-scale point clouds is of significant importance in environment perception and scene understanding. However, point clouds collected from real-world environments are usually imbalanced and small-sized objects are prone to

Externí odkaz: http://arxiv.org/abs/2409.13983

Zobrazit plný text záznamu