arXiv:1509.04232
공식 코드 · Papers with Code
gSLICr: SLIC superpixels at over 250Hz
원문 초록
We introduce a parallel GPU implementation of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Using a single graphic card, our implementation achieves speedups of up to $83\times$ from the standard sequential implementation. Our implementation is fully compatible with the standard sequential implementation and the software is now available online and is open source.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Cross-Domain Few-Shot Semantic Segmentation
A Fast Palette Reordering Technique Based on GPU-Optimized Genetic Algorithms
ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation
CNTK: Microsoft's Open-Source Deep-Learning Toolkit
Lazy Random Walks for Superpixel Segmentation
Image Segmentation Based on Watershed and Edge Detection Techniques
토론
이 논문과 연결된 포럼 글이 아직 없습니다.