Tomer Peleg

Alexandra Dana, Nadav Carmel, Amit Shomer et al.

Transferring the absolute depth prediction capabilities of an estimator to a new domain is a task with significant real-world applications. This task is specifically challenging when images from the new domain are collected without ground-truth depth measurements, and possibly with sensors of different intrinsics. To overcome such limitations, a recent zero-shot solution was trained on an extensive training dataset and encoded the various camera intrinsics. Other solutions generated synthetic data with depth labels that matched the intrinsics of the new target data to enable depth-scale transfer between the domains. In this work we present an alternative solution that can utilize any existing synthetic or real dataset, that has a small number of images annotated with ground truth depth labels. Specifically, we show that self-supervised depth estimators result in up-to-scale predictions that are linearly correlated to their absolute depth values across the domain, a property that we model in this work using a single scalar. In addition, aligning the field-of-view of two datasets prior to training, results in a common linear relationship for both domains. We use this observed property to transfer the depth-scale from source datasets that have absolute depth labels to new target datasets that lack these measurements, enabling absolute depth predictions in the target domain. The suggested method was successfully demonstrated on the KITTI, DDAD and nuScenes datasets, while using other existing real or synthetic source datasets, that have a different field-of-view, other image style or structural content, achieving comparable or better accuracy than other existing methods that do not use target ground-truth depths.

Yuval Becker, Raz Z. Nossek, Tomer Peleg

Image demosaicing is an important step in the image processing pipeline for digital cameras. In data centric approaches, such as deep learning, the distribution of the dataset used for training can impose a bias on the networks' outcome. For example, in natural images most patches are smooth, and high-content patches are much rarer. This can lead to a bias in the performance of demosaicing algorithms. Most deep learning approaches address this challenge by utilizing specific losses or designing special network architectures. We propose a novel approach, SDAT, Sub-Dataset Alternation Training, that tackles the problem from a training protocol perspective. SDAT is comprised of two essential phases. In the initial phase, we employ a method to create sub-datasets from the entire dataset, each inducing a distinct bias. The subsequent phase involves an alternating training process, which uses the derived sub-datasets in addition to training also on the entire dataset. SDAT can be applied regardless of the chosen architecture as demonstrated by various experiments we conducted for the demosaicing task. The experiments are performed across a range of architecture sizes and types, namely CNNs and transformers. We show improved performance in all cases. We are also able to achieve state-of-the-art results on three highly popular image demosaicing benchmarks.

Alexandra Dana, Maor Shutman, Yotam Perlitz et al.

General object detectors use powerful backbones that uniformly extract features from images for enabling detection of a vast amount of object types. However, utilization of such backbones in object detection applications developed for specific object types can unnecessarily over-process an extensive amount of background. In addition, they are agnostic to object scales, thus redundantly process all image regions at the same resolution. In this work we introduce BLT-net, a new low-computation two-stage object detection architecture designed to process images with a significant amount of background and objects of variate scales. BLT-net reduces computations by separating objects from background using a very lite first-stage. BLT-net then efficiently merges obtained proposals to further decrease processed background and then dynamically reduces their resolution to minimize computations. Resulting image proposals are then processed in the second-stage by a highly accurate model. We demonstrate our architecture on the pedestrian detection problem, where objects are of different sizes, images are of high resolution and object detection is required to run in real-time. We show that our design reduces computations by a factor of x4-x7 on the Citypersons and Caltech datasets with respect to leading pedestrian detectors, on account of a small accuracy degradation. This method can be applied on other object detection applications in scenes with a considerable amount of background and variate object sizes to reduce computations.