Scene understanding plays a crucial role in autonomous driving by utilizing sensory data for contextual information extraction and decision making. Beyond modeling advances, the …
L Kong, J Ren, L Pan, Z Liu - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Densely annotating LiDAR point clouds is costly, which often restrains the scalability of fully- supervised learning methods. In this work, we study the underexplored semi-supervised …
Multimodal fusion can make semantic segmentation more robust. However, fusing an arbitrary number of modalities remains underexplored. To delve into this problem, we create …
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully …
Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a …
Although various 3D datasets with different functions and scales have been proposed recently, it remains challenging for individuals to complete the whole pipeline of large-scale …
Semantic scene completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the …
Semantic segmentation in 3D meshes is the classification of its constituent element (s) into specific classes or categories. Using the powerful feature extraction abilities of deep neural …