Images　captured　in　low-light　conditions　usually　suffer　from　very　low　contrast　and　underexpose,　which　cannot　be　directly　utilized　in　the　subsequent　computer　vision　tasks,　such　as　object　recognition,　detection,　identification　and　tracking.　Existing　methods　include　HE　based　method,　Retinex　theory　based　method　and　deep　learning　method　which　may　generate　undesirable　enhanced　results　including　amplified　noise,　biased　colors　and　extreme　boundary.　To　address　this　problem,　we　utilize　prior　knowledge　of　Retinex　theory　and　GAN　based　on　data　statistic　to　propose　a　progressive　GAN-based　Transfer　network　to　realize　the　low-light　enhancement.　In　this　paper,　the　image　is　decomposed　by　JieP　method　based　on　the　Retinex　model　to　obtain　the　reflection　and　light　components,　and　learn　the　relationship　between　the　reflection　component　of　the　low-light　image　and　normal　light　image　via　a　reflection　decomposition　on　network　(RefDecN),　and　then　generate　the　reflection　component　of　the　low-light　image.　Then,　another　illumination　transfering　network　(IllumTransN)　is　utilized　to　transfer　the　light　of　normal　light　image　to　the　reflection　component　to　realize　low-light　enhancement.　Experimental　results　of　low-light　image　enhancement　on　RAISE,　LOL　and　MEF　datasets　demonstrate　our　ProGAN　can　outperform　state-of-the-art　methods　in　terms　of　objective　and　subjective　quality.