Fig. 6 | Scientific Reports

Fig. 6

From: A two-stage multi-scale attention-based network for weakly supervised cataract fundus image enhancement

Fig. 6

Visual comparison on ablation study. (a) Represents using synthetic cataract images by simulate formulation directly without the first stage and without multi-scale feature extraction. (b) Represents using synthetic cataract images by simulate formulation directly without the first stage. (c) Represents without multi-scale feature extraction. (d) Represents our method, utilizing both the first stage and multi-scale feature extraction. The magnified areas are indicated by green boxes in the retinal image.

Back to article page