Related papers: Linton Stereo Illusion: Response on Johnston (1991…
The 21 cm line of neutral hydrogen is a promising probe of the Epoch of Reionization (EoR) but suffers from contamination by spectrally smooth foregrounds, which obscure the large-scale signal along the line of sight. We explore the…
Why does our visual system fail to reconstruct reality, when we look at certain patterns? Where do Geometrical illusions start to emerge in the visual pathway? How far should we take computational models of vision with the same visual…
Estimating the confidence of disparity maps inferred by a stereo algorithm has become a very relevant task in the years, due to the increasing number of applications leveraging such cue. Although self-supervised learning has recently spread…
Retinal implants aim to restore functional vision despite photoreceptor degeneration, yet are fundamentally constrained by low resolution electrode arrays and patient-specific perceptual distortions. Most deployed encoders rely on…
Stereo video retargeting aims to resize an image to a desired aspect ratio. The quality of retargeted videos can be significantly impacted by the stereo videos spatial, temporal, and disparity coherence, all of which can be impacted by the…
Recent studies on interpretability of attention distributions have led to notions of faithful and plausible explanations for a model's predictions. Attention distributions can be considered a faithful explanation if a higher attention…
A critical aspect of human visual perception is the ability to parse visual scenes into individual objects and further into object parts, forming part-whole hierarchies. Such composite structures could induce a rich set of semantic concepts…
Stereoscopic 3D (S3D) displays provide an additional sense of depth compared to non-stereoscopic displays by sending slightly different images to the two eyes. But conventional S3D displays do not reproduce all natural depth cues. In…
Visual perceptions often come with illusions whose physical origin are not well understood yet. The encoding of stochastic light intensity $x(t)$ into spikes with firing rate $r(t)$ at time $t$ is investigated in an experiment with retinas…
Sparse coding has been proposed as a theory of visual cortex and as an unsupervised algorithm for learning representations. We show empirically with the MNIST dataset that sparse codes can be very sensitive to image distortions, a behavior…
The theory of General Relativity predicts that, since massive bodies curve spacetime, light from a distant source would be deflected by a foreground massive object -- a phenomenon known as \emph{Gravitational Lensing}. Historically, the…
When our eyes are presented with the same image, the brain processes it to view it as a single coherent one. The lateral shift in the position of our eyes, causes the two images to possess certain differences, which our brain exploits for…
We provide the first perceptual quantification of user's sensitivity to radial optic flow artifacts and demonstrate a promising approach for masking this optic flow artifact via blink suppression. Near-eye HMDs allow users to feel immersed…
Nighttime stereo depth estimation is still challenging, as assumptions associated with daytime lighting conditions do not hold any longer. Nighttime is not only about low-light and dense noise, but also about glow/glare, flares, non-uniform…
Computed Tomography (CT) reconstruction is a fundamental component to a wide variety of applications ranging from security, to healthcare. The classical techniques require measuring projections, called sinograms, from a full 180$^\circ$…
Two groundbreaking new facilities will commence operations early in the 2020s and thereafter define much of the broad landscape of US optical-infrared astronomy in the remaining decade. The Large Synoptic Survey Telescope (LSST), perched…
Stochastic resonance (SR) - a counter-intuitive phenomenon in which the signal due to a weak periodic force in a nonlinear system can be {\it enhanced} by the addition of external noise - is reviewed. A theoretical approach based on linear…
Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream applications, the learned representations often lack…
We propose a novel visual context-aware filter generation module which incorporates contextual information present in images into Convolutional Neural Networks (CNNs). In contrast to traditional CNNs, we do not employ the same set of…
Although Video Large Language Models perform remarkably well across tasks such as video understanding, question answering, and reasoning, they still suffer from the problem of hallucination, which refers to generating outputs that are…