Related papers: A bio-inspired image coder with temporal scalabili…
In recent years, there has been a sharp increase in transmission of images to remote servers specifically for the purpose of computer vision. In many applications, such as surveillance, images are mostly transmitted for automated analysis,…
While computer vision models have made incredible strides in static image recognition, they still do not match human performance in tasks that require the understanding of complex, dynamic motion. This is notably true for real-world…
U-Net has become one of the state-of-the-art deep learning-based approaches for modern computer vision tasks such as semantic segmentation, super resolution, image denoising, and inpainting. Previous extensions of U-Net have focused mainly…
Traditional artificial neural networks consist of nodes with non-oscillatory dynamics. Biological neural networks, on the other hand, consist of oscillatory components embedded in an oscillatory environment. Motivated by this feature of…
In studying primate vision, a large body of work focuses on the first feedforward sweep. During this initial time window, information is thought to pass through ventral stream regions in a stage-like fashion in an effort to extract…
There has been a strong push recently to examine biological scale simulations of neuromorphic algorithms to achieve stronger inference capabilities. This paper presents a set of piecewise linear spiking neuron models, which can reproduce…
The evaluation and monitoring of cells health in the human retina is crucial and follow time course of retinal diseases, detect lesions before irreversible visual loss and to evaluate treatment effects. Towards this goal, a major challenge…
Human vision achieves remarkable perceptual performance while operating under strict metabolic constraints. A key ingredient is the selective attention mechanism, driven by rapid saccadic eye movements that constantly reposition the…
We propose a novel theoretical biomolecular design to implement any Boolean circuit using the mechanism of DNA strand displacement. The design is scalable: all species of DNA strands can in principle be mixed and prepared in a single test…
Predictive coding is an influential model of cortical neural activity. It proposes that perceptual beliefs are furnished by sequentially minimising "prediction errors" - the differences between predicted and observed data. Implicit in this…
There has been significant research over the past two decades in developing new platforms for spiking neural computation. Current neural computers are primarily developed to mimick biology. They use neural networks which can be trained to…
Early processing of visual information takes place in the human retina. Mimicking neurobiological structures and functionalities of the retina provide a promising pathway to achieving vision sensor with highly efficient image processing.…
This study presents a theoretical model for a self-replicating mechanical system inspired by biological processes within living cells and supported by computer simulations. The model decomposes self-replication into core components, each of…
Human motion stylization aims to revise the style of an input motion while keeping its content unaltered. Unlike existing works that operate directly in pose space, we leverage the latent space of pretrained autoencoders as a more…
In this study, we present evidence suggesting that depthwise convolutional kernels are effectively replicating the structural intricacies of the biological receptive fields observed in the mammalian retina. We provide analytics of trained…
We develop a model for representing visual texture in a low-dimensional feature space, along with a novel self-supervised learning objective that is used to train it on an unlabeled database of texture images. Inspired by the architecture…
We demonstrate the feasibility of high-quality digital holography of the human retina in real-time with a fast camera and commodity computer hardware. High throughput rendering of digital Fresnel holograms from optically-acquired inline…
Integration between biology and information science benefits both fields. Many related models have been proposed, such as computational visual cognition models, computational motor control models, integrations of both and so on. In general,…
Dynamics play a critical role in computation. The principled evolution of states over time enables both biological and artificial networks to represent and integrate information to make decisions. In the past few decades, significant…
Clean images are an important requirement for machine vision systems to recognize visual features correctly. However, the environment, optics, electronics of the physical imaging systems can introduce extreme distortions and noise in the…