Deep Multimodal Fusion Autoencoder for Saliency Prediction of RGB-D Images

Figure 2

The results of various saliency models. (a) RGB. (b) GT. (c) Itti. (d) GBVS. (e) QFT. (f) Fang. (g) Qi. (h) DeepFix. (i) ML-net. (j) DVA. (k) Proposed.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)

(i)

(j)

(k)