4 papers · 1 filter
Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs
Chongyu Wang, Ting Huang, Chunyu Sun +3
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in 2D visual tasks but still struggle to understand physical space in real-world visual streams. Recently…
OpenUrban3D: Annotation-Free Open-Vocabulary Semantic Segmentation of Large-Scale Urban Point Clouds
Chongyu Wang, Kunlei Jing, Jihua Zhu +1
Open-vocabulary semantic segmentation enables models to recognize and segment objects from arbitrary natural language descriptions, offering the flexibility to handle novel, fine-g…
Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Datasets
Jing Liu, Duanchu Wang, Haoran Gong +3
Understanding and analyzing the spatial semantics and structure of forests is essential for accurate forest resource monitoring and ecosystem research. However, the lack of large-s…
Efficiently Expanding Receptive Fields: Local Split Attention and Parallel Aggregation for Enhanced Large-scale Point Cloud Semantic Segmentation
Haodong Wang, Chongyu Wang, Yinghui Quan +1
Expanding the receptive field in a deep learning model for large-scale 3D point cloud segmentation is an effective technique for capturing rich contextual information, which conseq…