Inaccuracy-Tolerant Sparse-to-Dense Depth Propagation for Semiautomatic 2D-to-3D Conversion

Figure 4

Results for RGBZ_01 in the absence of inaccurate scribbles. (a) Input image. (b) User scribbles. (c) Groundtruth. (d) Depth of RW [4]. (e) Depth of OPT [6]. (f) Depth of HGR [10]. (g) Depth of SOPT [13]. (h) Depth of NRW [14]. (i) Depth of proposed.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)

(i)