Related papers: Spatiotemporal focusing does not always improve ax…
In this paper we develop a method capable of modeling the space-time focusing of nondiffracting pulses. The new pulses can possess arbitrary peak velocities and, in addition to being resistant to diffraction, can have their peak intensities…
High-dynamic scene optical flow is a challenging task, which suffers spatial blur and temporal discontinuous motion due to large displacement in frame imaging, thus deteriorating the spatiotemporal feature of optical flow. Typically,…
An analytical description of arbitrary strongly aberrated axially symmetric focusing is developed. This is done by matching the solution of geometrical optics with a wave pattern which is universal for the underlying ray structure. The…
Self-Attention has become prevalent in computer vision models. Inspired by fully connected Conditional Random Fields (CRFs), we decompose self-attention into local and context terms. They correspond to the unary and binary terms in CRF and…
Recent advances in active noise control have enabled the development of hearables with spatial selectivity, which actively suppress undesired noise while preserving desired sound from specific directions. In this work, we propose an…
We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios. The key idea is to leverage the spatiotemporal nature of a dynamic point cloud sequence and introduce drastically…
Scattering prevents light from being focused in turbid media. The effect of scattering can be negated through wavefront shaping techniques when a localized form of feedback is available. Even in the absence of such a localized reporter,…
It is commonly accepted that optical sub-Rayleigh imaging has potential application in many fields. In this Letter, by confining the divergence of the optical field, as well as the size of the illumination source, we show that the…
We have theoretically investigated the focusing of a launched cloud of cold atoms. Time-dependent spatially-varying magnetic fields are used to impart impulses leading to a three-dimensional focus of the launched cloud. We discuss possible…
We demonstrate that deep learning methods can determine the best focus position from 1-2 image samples, enabling 5-10x faster focus than traditional search-based methods. In contrast with phase detection methods, deep autofocus does not…
Here, results are presented on the focusing of $1 \ \mu$m polystyrene particle suspensions using a synchronous oscillatory pressure-driven flow and oscillatory electric field in a microfluidic device. The effect of the phase difference…
Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…
Self-attention has become increasingly popular in a variety of sequence modeling tasks from natural language processing to recommendation, due to its effectiveness. However, self-attention suffers from quadratic computational and memory…
While a physical theory should be independent of the coordinate frame chosen by any observer, the observations themselves in fact depend on the choice of coordinates. In particular, different coordinate frames reflect different symmetries…
Light is the tool of the 21st century. New photosensitive tools offer the possibility to monitor and control neuronal activity from the sub-cellular to the integrative level. This ongoing revolution has motivated the development of new…
Wavefront shaping techniques allow waves to be focused on a diffraction-limited target deep inside disordered media. To identify the target position, a guidestar is required that typically emits a frequency-shifted signal. Here we present a…
This paper tackles the challenging problem of estimating the intensity of Facial Action Units with few labeled images. Contrary to previous works, our method does not require to manually select key frames, and produces state-of-the-art…
We study the focusing of light through random photonic materials using wavefront shaping. We explore a novel approach namely binary amplitude modulation. To this end, the light incident to a random photonic medium is spatially divided into…
We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…
Spatiotemporal predictive learning offers a self-supervised learning paradigm that enables models to learn both spatial and temporal patterns by predicting future sequences based on historical sequences. Mainstream methods are dominated by…