SiftGPU swMATH ID: 11748 Software Authors: Wu, C Description: SiftGPU: A GPU Implementation of Scale Invariant Feature Transform (SIFT). SiftGPU is an implementation of SIFT [1] for GPU. SiftGPU processes pixels parallely to build Gaussian pyramids and detect DoG Keypoints. Based on GPU list generation[3], SiftGPU then uses a GPU/CPU mixed method to efficiently build compact keypoint lists. Finally keypoints are processed parallely to get their orientations and descriptors. SiftGPU is inspired by Andrea Vedaldi’s sift++[2] and Sudipta N Sinha et al’s GPU-SIFT[4] . Many parameters of sift++ ( for example, number of octaves, number of DOG levels, edge threshold, etc) are also available in SiftGPU. The shader programs are dynamically generated according to the parameters that user specified. SiftGPU also includes a GPU exhaustive/guided sift matcher SiftMatchGPU. It basically multiplies the descriptor matrix on GPU and finds the closest feature matches on GPU. Both GLSL and CUDA implementations are provided. Homepage: http://cs.unc.edu/~ccwu/siftgpu/ Related Software: PCA-SIFT; Vlfeat; Soft scissors; SoftPOSIT; COIL-100; GrabCut; QBIC; FERET; LAPACK; openMVG; SURF; LEMON; DTAM; RT-SLAM; ORB-SLAM2; KITTI; ORB-SLAM; SVO; LSD-SLAM; MonoSLAM Cited in: 4 Publications all top 5 Cited by 11 Authors 1 Harasztos, Frigyes 1 Hollósi, Gergely 1 Li, Peihua 1 Lukovszki, Csaba 1 Moldován, István 1 Plósz, Sándor 1 Pu, Yuchi 1 Ren, Chaofeng 1 Szeliski, Richard 1 Zhang, Fuqiang 1 Zhi, Xiaodong Cited in 4 Serials 1 Journal of Mathematical Imaging and Vision 1 Mathematical Biosciences and Engineering 1 Acta Universitatis Sapientiae. Informatica 1 Texts in Computer Science Cited in 2 Fields 4 Computer science (68-XX) 1 Information and communication theory, circuits (94-XX) Citations by Year