Description

The 3D shape description dataset consists of multiple sub-datasets Descriptor Matching - Dataset 1 & 2 (Stanford) These datasets, created from some of the models belonging to the Stanford 3D Scanning Repository, are composed of 6 models and 45 scenes. Each of the 45 scenes contains a subset of the 6 models randomly chosen and randomly rotated and translated so to create clutter conditions. In particular, out of the 45 scenes the dataset contains 15 scenes with 3-5 models each. Descriptor Matching - Dataset 3 (Spacetime Stereo) This dataset, acquired in our lab by means of the Spacetime Stereo technique, is composed of 8 models and 15 scenes, divided into 4 sets as follows: 2 scenes with 3-4 models each. Descriptor Matching - Dataset 4 (Spacetime Stereo Texture) This dataset, acquired in our lab by means of the Spacetime Stereo technique, is composed of 8 models and 16 scenes, divided into 4 sets as follows: 2 scenes with 4 models each. Descriptor Matching - Dataset 5 (Kinect) This dataset, acquired in our lab by means of the Microsoft Kinect sensor, is composed of 7 models and 17 scenes. Reconstruction - Space Time Views This dataset, acquired in our lab by means of the Microsoft Space Time technique, is composed of several views of 2 objects ("Mario" and "Squirell"). Only the "Mario" views were used in [1]. Reconstruction - Kinect Views This dataset, acquired in our lab by means of the Microsoft Kinect sensor, is composed of several views of 2 objects ("Frog" and "Duck"). References [1] F. Tombari *, S. Salti *, L. Di Stefano, "Unique Signatures of Histograms for Local Surface Description", ECCV 2010 [2] F. Tombari, S. Salti, L. Di Stefano, "A combined texture-shape descriptor for enhanced 3D feature matching", ICIP 2011

Related datasets