Adding Non-Linear Context To Deep Networks
Michele Covell, David Marwood, Shumeet Baluja
-
Members: FreeSPS
IEEE Members: $11.00
Non-members: $15.00Length: 00:10:04
17 Oct 2022
We consider the perceptual quality optimization in image coding through adaptive quantization. A differential contrast model is proposed to measure the visual sensitivity to the quantization distortions, and thereby deriving the spatially adaptive quantization strategy. A complementary quantitative approach is provided as a means to efficiently calculate the proposed differential contrast model. The resulting visual quality improvement is experimentally demonstrated.
