Self-generated Defocus Blur Detection via Dual Adversarial Discriminators

Abstract

Although existing fully-supervised defocus blur detection (DBD) models significantly improve performance, training such deep models requires abundant pixel-level manual annotation, which is highly time-consuming and error-prone. Addressing this issue, this paper makes an effort to train a deep DBD model without using any pixel-level annotation. The core insight is that a defocus blur region/focused clear area can be arbitrarily pasted to a given realistic full blurred image/full clear image without affecting the judgment of the full blurred image/full clear image. Specifically, we train a generator G in an adversarial manner against dual discriminators D <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">c</inf> and D <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">b</inf> . G learns to produce a DBD mask that generates a composite clear image and a composite blurred image through copying the focused area and unfocused region from corresponding source image to another full clear image and full blurred image. Then, D <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">c</inf> and D <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">b</inf> can not distinguish them from realistic full clear image and full blurred image simultaneously, achieving a self-generated DBD by an implicit manner to define what a defocus blur area is. Besides, we propose a bilateral triplet-excavating constraint to avoid the degenerate problem caused by the case one discriminator defeats the other one. Comprehensive experiments on two widely-used DBD datasets demonstrate the superiority of the proposed approach. Source codes are available at: https://github.com/shangcai1/SG.