Hierarchical Multimodal Adaptive Fusion (HMAF) Network for Prediction of RGB-D Saliency

Figure 5

Qualitative results. (a) Ground-truth, (b) Proposed, (c) Fang, (d) DeepFix, (e) DVA, (f) SAM, (g) EML, and (h) SMI.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)