Aaron Wetzler

Roman Rabinovich, Ibrahim Jubran, Aaron Wetzler et al.

This paper presents a novel beacon light coding protocol, which enables fast and accurate identification of the beacons in an image. The protocol is provably robust to a predefined set of detection and decoding errors, and does not require any synchronization between the beacons themselves and the optical sensor. A detailed guide is then given for developing an optical tracking and localization system, which is based on the suggested protocol and readily available hardware. Such a system operates either as a standalone system for recovering the six degrees of freedom of fast moving objects, or integrated with existing SLAM pipelines providing them with error-free and easily identifiable landmarks. Based on this guide, we implemented a low-cost positional tracking system which can run in real-time on an IoT board. We evaluate our system's accuracy and compare it to other popular methods which utilize the same optical hardware, in experiments where the ground truth is known. A companion video containing multiple real-world experiments demonstrates the accuracy, speed, and applicability of the proposed system in a wide range of environments and real-world tasks. Open source code is provided to encourage further development of low-cost localization systems integrating the suggested technology at its navigation core.

Ron Slossberg, Aaron Wetzler, Ron Kimmel

Stereo reconstruction from rectified images has recently been revisited within the context of deep learning. Using a deep Convolutional Neural Network to obtain patch-wise matching cost volumes has resulted in state of the art stereo reconstruction on classic datasets like Middlebury and Kitti. By introducing this cost into a classical stereo pipeline, the final results are improved dramatically over non-learning based cost models. However these pipelines typically include hand engineered post processing steps to effectively regularize and clean the result. Here, we show that it is possible to take a more holistic approach by training a fully end-to-end network which directly includes regularization in the form of a densely connected Conditional Random Field (CRF) that acts as a prior on inter-pixel interactions. We demonstrate that our approach on both synthetic and real world datasets outperforms an alternative end-to-end network and compares favorably to more hand engineered approaches.

Gautam Pai, Aaron Wetzler, Ron Kimmel

We propose a metric learning framework for the construction of invariant geometric functions of planar curves for the Eucledian and Similarity group of transformations. We leverage on the representational power of convolutional neural networks to compute these geometric quantities. In comparison with axiomatic constructions, we show that the invariants approximated by the learning architectures have better numerical qualities such as robustness to noise, resiliency to sampling, as well as the ability to adapt to occlusion and partiality. Finally, we develop a novel multi-scale representation in a similarity metric learning paradigm.

Roy Or - El, Rom Hershkovitz, Aaron Wetzler et al.

The introduction of consumer RGB-D scanners set off a major boost in 3D computer vision research. Yet, the precision of existing depth scanners is not accurate enough to recover fine details of a scanned object. While modern shading based depth refinement methods have been proven to work well with Lambertian objects, they break down in the presence of specularities. We present a novel shape from shading framework that addresses this issue and enhances both diffuse and specular objects' depth profiles. We take advantage of the built-in monochromatic IR projector and IR images of the RGB-D scanners and present a lighting model that accounts for the specular regions in the input image. Using this model, we reconstruct the depth map in real-time. Both quantitative tests and visual evaluations prove that the proposed method produces state of the art depth reconstruction results.

Aaron Wetzler, Ron Slossberg, Ron Kimmel

We investigate a novel global orientation regression approach for articulated objects using a deep convolutional neural network. This is integrated with an in-plane image derotation scheme, DeROT, to tackle the problem of per-frame fingertip detection in depth images. The method reduces the complexity of learning in the space of articulated poses which is demonstrated by using two distinct state-of-the-art learning based hand pose estimation methods applied to fingertip detection. Significant classification improvements are shown over the baseline implementation. Our framework involves no tracking, kinematic constraints or explicit prior model of the articulated object in hand. To support our approach we also describe a new pipeline for high accuracy magnetic annotation and labeling of objects imaged by a depth camera.