Transformation-Grounded Image Generation Network for Novel 3D View Synthesis – Supplementary Material

We show an experiment on the generalization capability for arbitrary transformations. Although we have trained the network with 17 discrete transformations in the range [20,340] with 20-degree increments, our trained network can synthesize arbitrary view points with linear interpolations of one-hot vectors. For example, if [0,1,0,0,...0] and [0,0,1,0,...0] represent 40 and 60-degree transformations respectively, [0,0.5,0.5,0,...0] represents 50 degree. More formally, let t ∈ [0, 1] be encoding vector for the transformation parameter θ ∈ [20, 340] and s be step size (s = 20). For a transformation parameter i × s ≤ θ < (i + 1) × s, i and i+ 1 elements of the encoding vector t is