AdelaideRMF: Robust Model Fitting Data Set AdelaideRMF is a data set for robust geometric model fitting (homography estimation and fundamental matrix estimation). We collected a set of image pairs and manually labelled the keypoint correspondences which were obtained by SIFT matching. Each Matlab .mat file contains: img1 - left image img2 - right image data - keypoint correspondences (x1,y1,1,x2,y2,1) where (x1,y1) in img1 and (x2,y2) in img2 score - SIFT correspondences matching score label - 0 indicates gross outliers and others indicate the structure membership The complete dataset can be downloaded here. To download the individual data, please click the data name below. Hoi Sim Wong, Tat-Jun Chin, Jin Yu, and David Suter, Dynamic and Hierarchical Multi-Structure Geometric Model Fitting, International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011. For enquires regarding this data set, please email hoi.wong@adelaiade.edu.au See also http://cs.adelaide.edu.au/~dsuter/code_and_data/hanzi_2011_fitting/ Simultaneously Fitting and Segmenting Multiple-Structural Data with Outliers", H. Wang, T-J Chin and D. Suter
The CALTECH 101 Category Patch Pairs dataset measures invariance to intra-category variation. The dataset contains a training set and testing set of imag…
binary, feature description, feature matching, pairThe DTU Robot dataset consists of color images of 60 scenes acquired in a controlled setup from 119 different positions and under different lighting. For …
feature description, feature detection, feature matching, illumination, reconstruction, sfmThe Synthetic CAD Models dataset consists of X synthetic CAD models for detection (planar) primitives. Efficient RANSAC for Point-Cloud Shape Detection …
3d object, model fitting, primitive, ransac, reconstruction, syntheticThe SAMANTHA (Structure-and-Motion Pipeline on a Hierarchical Cluster Tree) dataset contains 4 sequences for 3D reconstruction: Pozzoveggiani, Piazza Dant…
3d reconstruction, geometry, landmark, model fitting, sfmThe data is taken from Photo Tourism reconstructions from Trevi Fountain (Rome), Notre Dame (Paris) and Half Dome (Yosemite). Each dataset consists of a s…
feature description, feature matching, pair, sfm