Related papers: 1000x Faster Camera and Machine Vision with Ordina…
Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image. However, there are still gaps in both performance and computational cost between…
We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…
We present a method that leverages the complementarity of event cameras and standard cameras to track visual features with low-latency. Event cameras are novel sensors that output pixel-level brightness changes, called "events". They offer…
Event-based cameras have recently drawn the attention of the Computer Vision community thanks to their advantages in terms of high temporal resolution, low power consumption and high dynamic range, compared to traditional frame-based…
We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual…
Event cameras are a paradigm shift in camera technology. Instead of full frames, the sensor captures a sparse set of events caused by intensity changes. Since only the changes are transferred, those cameras are able to capture quick…
There are two critical sensors for 3D perception in autonomous driving, the camera and the LiDAR. The camera provides rich semantic information such as color, texture, and the LiDAR reflects the 3D shape and locations of surrounding…
Machine vision systems using convolutional neural networks (CNNs) for robotic applications are increasingly being developed. Conventional vision CNNs are driven by camera frames at constant sample rate, thus achieving a fixed latency and…
Unlike conventional cameras which capture video at a fixed frame rate, Dynamic Vision Sensors (DVS) record only changes in pixel intensity values. The output of DVS is simply a stream of discrete ON/OFF events based on the polarity of…
Traditionally, video is structured as a sequence of discrete image frames. Recently, however, a novel video sensing paradigm has emerged which eschews video frames entirely. These "event" sensors aim to mimic the human vision system with…
Traditional glass-based optics are typically optimized for narrow spectral bands, such as the visible (400-700nm) or shortwave infrared (1000-1800nm). While the emergence of VIS-SWIR sensors (400-1700nm) offers transformative potential,…
Modelling the mapping from scene irradiance to image intensity is essential for many computer vision tasks. Such mapping is known as the camera response. Most digital cameras use a nonlinear function to map irradiance, as measured by the…
Deploying advanced imaging solutions to robotic and autonomous systems by mimicking human vision requires simultaneous acquisition of multiple fields of views, named the peripheral and fovea regions. Low-resolution peripheral field provides…
Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…
Vision Transformers (ViT) have achieved remarkable success in large-scale image recognition. They split every 2D image into a fixed number of patches, each of which is treated as a token. Generally, representing an image with more tokens…
Autonomous vehicles operate in a dynamic environment, where the speed with which a vehicle can perceive and react impacts the safety and efficacy of the system. LiDAR provides a prominent sensory modality that informs many existing…
Vision Transformer models, such as ViT, Swin Transformer, and Transformer-in-Transformer, have recently gained significant traction in computer vision tasks due to their ability to capture the global relation between features which leads to…
Volumetric (4D) performance capture is fundamental for AR/VR content generation. Whereas previous work in 4D performance capture has shown impressive results in studio settings, the technology is still far from being accessible to a typical…
Super-resolution microscopy overcomes the diffraction limit of conventional light microscopy in spatial resolution. By providing novel spatial or spatio-temporal information on biological processes at nanometer resolution with molecular…
Recent work on Neural Radiance Fields (NeRF) showed how neural networks can be used to encode complex 3D environments that can be rendered photorealistically from novel viewpoints. Rendering these images is very computationally demanding…