Geometric and texture cue based depth-map estimation for 2D to 3D image conversion
Kyuseo Han, Kihyun Hong · 2011
We present a novel framework for estimating depth-map in a single 2D image. The proposed framework employs both vanishing point and superpixels as geometric and texture cues, respectively. The combination of both cues can generate a feasible perceptual depth-map, which will be applied to 2D to 3D image conversion.