Active vision therapy for amblyopia shows good results, but there is no standard vision therapy protocol. This study compared the results of three treatments, two combining patching with active therapy and one with patching alone, in a sample of children with amblyopia. Two protocols have been developed: (a) perceptual learning with a computer game designed to favour the medium-to-high spatial frequency-tuned achromatic mechanisms of parvocellular origin and (b) vision therapy with a specific protocol and 2-h patching. The third treatment group used patching only. Fifty-two amblyopic children (aged 4-12 years), were randomly assigned to three monocular treatment groups: 2-h patching (n = 18), monocular perceptual learning (n = 17) and 2-h patching plus vision therapy (n = 17). Visual outcomes were analysed after 3 months and compared with a control group (n = 36) of subjects with normal vision. Visual acuity (VA) and stereoacuity (STA) improved significantly after treatment for the three groups with the best results for patching plus vision therapy, followed by monocular perceptual learning, with patching only least effective. Change in the interocular difference in VA was significant for monocular perceptual learning, followed by patching. Differences in STA between groups were not significant. For VA and interocular differences, the final outcomes were influenced by the baseline VA and interocular difference, respectively, with greater improvements in subjects with poorer initial values. Visual acuity and STA improved with the two most active treatments, that is, vision therapy followed by perceptual learning. Patching alone showed the worst outcome. These results suggest that vision therapy should include monocular accommodative exercises, ocular motility and central fixation exercises where the fovea is more active.