No abstract

In recent years, self-supervised monocular depth estimation has drawn much attention since it frees of depth annotations and achieved remarkable results on standard benchmarks. However, most of existing methods only focus on either daytime or nighttime images, thus their performance degrades on the other domain because of the large domain shift between daytime and nighttime images. To address this problem, in this paper we propose a two-branch network named GlocalFuse-Depth for self-supervised depth estimation of all-day images. The daytime and nighttime image in input image pair are fed into the two branches: CNN branch and Transformer branch, respectively, where both fine-grained details and global dependency can be efficiently captured. Besides, a novel fusion module is proposed to fuse multi-dimensional features from the two branches. Extensive experiments demonstrate that GlocalFuse-Depth achieves state-of-the-art results for all-day images on the Oxford RobotCar dataset, which proves the superiority of our method.

We demonstrate the use of spiral phase modulation in preprocessing defocused image before feeding into deep learning model for autofocusing. Average predict error is shown to outperform previously published works on an open dataset.

We demonstrate the use of conditional generative adversarial network in restoring undersampled two-photon microscopic image. Image resolution and contrast can be substantially improved without noticeable artefacts with a 4-fold increase in imaging speed.

We demonstrated image quality enhancement by deconvolution for non-diffracting beam confocal two-photon microscopy. Through a custom Bessel/Airy point spread function (PSF) and Richardson-Lucy algorithm, we achieved > 7.0 dB increase in signal-to-background ratio (SBR).