Single image super resolution aims to enhance image quality with respect to spatial content, which is a fundamental task in computer vision. In this work, we address the task of single frame super resolution with the presence of image degradation, e.g., blur, haze, or rain streaks. Due to the limitations of frame capturing and formation processes, image degradation is inevitable, and the artifacts would be exacerbated by super resolution methods. To address this problem, we propose a dual-branch convolutional neural network to extract base features and recovered features separately. The base features contain local and global information of the input image. On the other hand, the recovered features focus on the degraded regions and are used to remove the degradation. Those features are then fused through a recursive gate module to obtain sharp features for super resolution. By decomposing the feature extraction step into two task-independent streams, the dual-branch model can facilitate the training process by avoiding learning the mixed degradation all-in-one and thus enhance the final high-resolution prediction results. We evaluate the proposed method in three degradation scenarios. Experiments on these scenarios demonstrate that the proposed method performs more efficiently and favorably against the state-of-the-art approaches on benchmark datasets.
Ramsey interferometers (RIs) using internal electronic or nuclear states find wide applications in science and engineering. We develop a matter wave Ramsey interferometer for motional quantum states exploiting the S-and D-bands of an optical lattice and identify the different de-phasing and de-coherence mechanisms. We implement a band echo technique, employing repeated π-pulses. This suppresses the de-phasing evolution and significantly increase the coherence time of the motional state interferometer by one order of magnitude. We identify thermal fluctuations as the main mechanism for the remaining decay contrast. Our demonstration of an echo-Ramsey interferometer with motional quantum states in an optical lattice has potential application in the study of quantum many body lattice dynamics, and motional qubits manipulation.
We report the observation of quantum dynamical oscillations of ultracold atomic gases in the F and D bands of a single-well optical lattice. We are able to control the Bragg reflections at the Brillouin zone edge up to the third order. As a result, we can switch the quantum dynamics from oscillations across both the F and D bands to oscillations only within the F-band. Our capability to observe these remarkable oscillations comes from the innovative non-adiabatic technique which allows us to load ultracold atoms efficiently to the G-band of an optical lattice.
We report the long-time nonlinear dynamical evolution of ultracold atomic gases in the P-band of an optical lattice. A Bose-Einstein condensate (BEC) is fast and efficiently loaded into the Pband at zero quasi-momentum with a non-adiabatic shortcut method. For the first one and half milliseconds, these momentum states undergo oscillations due to coherent superposition of different bands, which are followed by oscillations up to 60ms of a much longer period. Our analysis shows the dephasing from the nonlinear interaction is very conducive to the long-period oscillations induced by the variable force due to the harmonic confinement.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.