This Camera-only 3D occupancy estimation aims to cost-effectively reconstruct the occupancy state of a grid of voxels in a three-dimensional space, based on input from several cameras. One of the limitations of this approach is detecting occupied voxels of objects located far away, since the cameras resolution at such distances is relatively low. In this work, we boost performance by introducing gaze map estimation. Specifically, we show that although no additional sensor is used, gaze map estimation is strong enough and can be used to enhance basic occupancy estimation networks, yielding better Chamfer distance (CD), F-score and intersection over union (IoU) metrics. At long distances, we found an improvement over the baseline of more than 20% in CD, 24% in F-score and 15% in IoU.

In the process of training Neural Networks, pre-training is an unsupervised training process that uses automatically generated labels for real end-goal task inputs. It usually precedes a supervised training stage, can improve neural network performance, and can reduce training loss. In this work, we used pre-training in the automotive domain where the setup was composed of a camera aimed outside the vehicle and an eye tracking system observing the driver. Our pre-training process used images from the camera as input and eye gaze direction as the automatic generated label. The eye gaze pre-training goal was to initiate and thus improve disparity estimation networks.Selecting eye gaze as labels is the best of both worlds. On one hand, it is somewhat similar to supervised training. Labels are generated by humans, by drivers who have deep understanding of the scenes and driving situation. On the other hand, it is similar to unsupervised training. The labels can be generated automatically. Large quantities of data can be collected easily. Overall, the eye gaze pre-train helped reduce the L1 loss from 0.65 when not using pre-train to 0.45 when using it on the validation set.

MOTIVATION: The study of RNA virus populations is a challenging task. Each population of RNA virus is composed of a collection of different, yet related genomes often referred to as mutant spectra or quasispecies. Virologists using deep sequencing technologies face major obstacles when studying virus population dynamics, both experimentally and in natural settings due to the relatively high error rates of these technologies and the lack of high performance pipelines. In order to overcome these hurdles we developed a computational pipeline, termed ViVan (Viral Variance Analysis). ViVan is a complete pipeline facilitating the identification, characterization and comparison of sequence variance in deep sequenced virus populations. RESULTS: Applying ViVan on deep sequenced data obtained from samples that were previously characterized by more classical approaches, we uncovered novel and potentially crucial aspects of virus populations. With our experimental work, we illustrate how ViVan can be used for studies ranging from the more practical, detection of resistant mutations and effects of antiviral treatments, to the more theoretical temporal characterization of the population in evolutionary studies. AVAILABILITY AND IMPLEMENTATION: Freely available on the web at http://www.vivanbioinfo.org CONTACT: : [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.