IPC-Net: 3D point-cloud segmentation using deep inter-point convolutional layers
원문 초록
Over the last decade, the demand for better segmentation and classification algorithms in 3D spaces has significantly grown due to the popularity of new 3D sensor technologies and advancements in the field of robotics. Point-clouds are one of the most popular representations to store a digital description of 3D shapes. However, point-clouds are stored in irregular and unordered structures, which limits the direct use of segmentation algorithms such as Convolutional Neural Networks. The objective of our work is twofold: First, we aim to provide a full analysis of the PointNet architecture to illustrate which features are being extracted from the point-clouds. Second, to propose a new network architecture called IPC-Net to improve the state-of-the-art point cloud architectures. We show that IPC-Net extracts a larger set of unique features allowing the model to produce more accurate segmentations compared to the PointNet architecture. In general, our approach outperforms PointNet on every family of 3D geometries on which the models were tested. A high generalisation improvement was observed on every 3D shape, especially on the rockets dataset. Our experiments demonstrate that our main contribution, inter-point activation on the network's layers, is essential to accurately segment 3D point-clouds.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model
APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds
3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation
GeoT: Geometry-guided Instance-dependent Transition Matrix for Semi-supervised Tooth Point Cloud Segmentation
Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.