Authors: Engin Tola, Vincent Lepetit, Pascal Fua

Keywords:

• Stereo image
• descriptor
• circle
• quantization
• formalization
• binary mask
• Depth estimation

Q1: How is depth estimation related to object recognition?

Objects are located in a 3D environment, and in order to recognize them correctly, we need to be able to recreate their layout in a scene. With such an aid, we can successfully determine the object boundaries.

Q2: What does the descriptor contain?

It is a concatenation of vectors. The first vector is the Gaussian of the center point with a $\Sigma_0$, the second set of vectors are circles lying on circle $R_1$, the third set of vectors are circles lying on circle $R_2$… Each vector contains orientation maps after a Gaussian convolution.

Q3: On which datasets did the authors try the technique?

As far as I can tell, it is a custom dataset that contains the view of the same scene from many perspectives.

Q4: What is the salience criterion for keypoints?

The aim of the technique is not matching these keypoints to each other by selecting the most appropriate ones. The computation is done on all pixels/keypoints. Hence, no criterion for keypoint filtering is reported.