Related papers: Scattering-induced entropy boost for highly-compre…

Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-based methods have high…

Nanoscale manufacturing requires high-precision surface inspection to guarantee the quality of the produced nanostructures. For production environments, angle-resolved scatterometry offers a non- invasive and in-line compatible alternative…

3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision. To combine information from different perspectives without troublesome 2D instance tracking, recent methods tend to aggregate…

Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely…

We investigate the performance of entropy estimation methods, based either on block entropies or compression approaches, in the case of bidimensional sequences. We introduce a validation dataset made of images produced by a large number of…

Elastic light scattering has been extensively used to study samples showing a non uniform refraction index on lengthscales from a fraction of a micrometer to a fraction of a millimeter. Typically, a wide laser beam is sent through the…

A new concept of a free-space, high-speed (Gbps) optical communication system based on spectral encoding of radiation from a broadband pulsed laser is developed. It is shown that, in combination with the use of partially coherent laser…

With advanced image journaling tools, one can easily alter the semantic meaning of an image by exploiting certain manipulation techniques such as copy-clone, object splicing, and removal, which mislead the viewers. In contrast, the…

Every day around the world, interminable terabytes of data are being captured for surveillance purposes. A typical 1-2MP CCTV camera generates around 7-12GB of data per day. Frame-by-frame processing of such enormous amount of data requires…

In this paper we tackle the problem of stereo image compression, and leverage the fact that the two images have overlapping fields of view to further compress the representations. Our approach leverages state-of-the-art single-image…

Transformers demonstrate competitive performance in terms of precision on the problem of vision-based object detection. However, they require considerable computational resources due to the quadratic size of the attention weights. In this…

We propose an optical encryption framework that can encrypt and decrypt large-sized images beyond the size of the encrypted image using our two methods: random phase-free method and scaled diffraction. In order to record the entire image…

We present a novel clustering objective that learns a neural network classifier from scratch, given only unlabelled data samples. The model discovers clusters that accurately match semantic classes, achieving state-of-the-art results in…

Photonic computation started to shape the future of fast, efficient and accessible computation. The advantages brought by light based Diffractive Deep Neural Networks (D2NN), are shown to be overwhelmingly advantageous especially in…

Imaging through a single optical fiber offers attractive possibilities in many applications such as microendoscopy or remote sensing. However, the direct transmission of an image through an optical fiber is difficult because spatial…

In recent times, with the exception of sporadic cases, the trend in Computer Vision is to achieve minor improvements compared to considerable increases in complexity. To reverse this trend, we propose a novel method to boost image…

The microwave imaging based on inverse scattering strategy holds important promising in the science, engineering, and military applications. Here we present a compressed-sensing (CS) inspired large- aperture computational single-sensor…

In this paper, we propose a lensless compressive imaging architecture. The architecture consists of two components, an aperture assembly and a sensor. No lens is used. The aperture assembly consists of a two dimensional array of aperture…

In this paper, we propose an efficient and fast object detector which can process hundreds of frames per second. To achieve this goal we investigate three main aspects of the object detection framework: network architecture, loss function…

Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…