DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation
원문 초록
Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis. In this paper, we propose DAR-Net, a novel network architecture that focuses on dynamic feature aggregation. The central idea of DAR-Net is generating a self-adaptive pooling skeleton that considers both scene complexity and local geometry features. Providing variable semi-local receptive fields and weights, the skeleton serves as a bridge that connect local convolutional feature extractors and a global recurrent feature integrator. Experimental results on indoor scene datasets show advantages of the proposed approach compared to state-of-the-art architectures that adopt static pooling methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking
The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefs
MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps
Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting
ROAD-Waymo: Action Awareness at Scale for Autonomous Driving
Surgical Scene Segmentation by Transformer With Asymmetric Feature Enhancement
토론
이 논문과 연결된 포럼 글이 아직 없습니다.