Abstract: Devices, systems, methods, and media are disclosed for domain adaptation using data densification. Example embodiments described herein receives LiDAR 3D point clouds from a source-domain and introduces interpolated 3D points inferred by a trained deep learning neural network to output a denser version of the input 3D point cloud with increased resolution. The trained domain adaptation network reconstructs the source-domain 3D point cloud data, generates translation vectors to compute interpolated 3D point cloud data and merges the reconstructed 3D point cloud data and the interpolated 3D point cloud data to output a densified 3D point cloud resembling data 3D point clouds captured generated by the target LiDAR sensor from the source-domain.

Abstract: Devices, systems, methods, and media are disclosed for domain adaptation of a trained machine learning model using hybrid learning. A hybrid approach to domain adaptation is disclosed that combines aspects of discrepancy-based, adversarial, and reconstruction-based approaches to achieve an end-to-end trained model for performing a prediction task (such as semantic segmentation) on a sparsely labeled dataset in a target domain, by leveraging a richly-labeled dataset in the source domain. Some embodiments may also provide a trained domain translation model for generating synthetic data samples in a first domain based on input data samples from a second domain.

Abstract: Global-adaptive deinterlacing systems and methods for reducing scintillation and feathering artifacts. Motion adaptive deinterlacing (MADI) local motion quantization thresholds are adaptively adjusted according to the amount of global motion present in the video sequence, thereby minimizing scintillation and feathering artifacts when deinterlacing the fields. A set of global motion scenarios are defined for the purpose of classifying fields, and a number of global motion indicators are used to detect on a field-by-field basis different global motion scenarios. The global motion indicators are corrected to reduce Luma dependencies, thereby improving reliability and robustness. Depending on the global motion scenario of a field, the local motion thresholds are adaptively adjusted. The adaptive adjustment of quantization thresholds are optionally also applied to temporal noise reduction and cross-color suppression.