SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing
원문 초록
Deep neural networks have established themselves as the state-of-the-art methodology in almost all computer vision tasks to date. But their application to processing data lying on non-Euclidean domains is still a very active area of research. One such area is the analysis of point cloud data which poses a challenge due to its lack of order. Many recent techniques have been proposed, spearheaded by the PointNet architecture. These techniques use either global or local information from the point clouds to extract a latent representation for the points, which is then used for the task at hand (classification/segmentation). In our work, we introduce a neural network layer that combines both global and local information to produce better embeddings of these points. We enhance our architecture with residual connections, to pass information between the layers, which also makes the network easier to train. We achieve state-of-the-art results on the ModelNet40 dataset with our architecture, and our results are also highly competitive with the state-of-the-art on the ShapeNet part segmentation dataset and the indoor scene segmentation dataset. We plan to open source our pre-trained models on github to encourage the research community to test our networks on their data, or simply use them for benchmarking purposes.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AI-Driven MRI-based Brain Tumour Segmentation Benchmarking
A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects
crossMoDA Challenge: Evolution of Cross-Modality Domain Adaptation Techniques for Vestibular Schwannoma and Cochlea Segmentation from 2021 to 2023
Learning Generalized Segmentation for Foggy-scenes by Bi-directional Wavelet Guidance
FTNet: Feature Transverse Network for Thermal Image Semantic Segmentation
Scene Segmentation with Dual Relation-aware Attention Network
토론
이 논문과 연결된 포럼 글이 아직 없습니다.