Related papers: 1000x Faster Camera and Machine Vision with Ordina…
The proliferation of single-photon image sensors has opened the door to a plethora of high-speed and low-light imaging applications. However, data collected by these sensors are often 1-bit or few-bit, and corrupted by noise and strong…
Animals such as insects have provided a rich source of inspiration for designing robots. For example, animals navigate to goals via efficient coordination of individual motor actions, and demonstrate natural solutions to problems also faced…
360$^{\circ}$ video requires human viewers to actively control "where" to look while watching the video. Although it provides a more immersive experience of the visual content, it also introduces additional burden for viewers; awkward…
Because image sensor chips have a finite bandwidth with which to read out pixels, recording video typically requires a trade-off between frame rate and pixel count. Compressed sensing techniques can circumvent this trade-off by assuming…
For 3D object detection, both camera and lidar have been demonstrated to be useful sensory devices for providing complementary information about the same scenery with data representations in different modalities, e.g., 2D RGB image vs 3D…
Video fusion is a process that combines visual data from different sensors to obtain a single composite video preserving the information of the sources. The availability of a system, enhancing human ability to perceive the observed…
In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper…
Capturing an event from multiple camera angles can give a viewer the most complete and interesting picture of that event. To be suitable for broadcasting, a human director needs to decide what to show at each point in time. This can become…
We present a data-driven approach for 4D space-time visualization of dynamic events from videos captured by hand-held multiple cameras. Key to our approach is the use of self-supervised neural networks specific to the scene to compose…
Single-pixel cameras based on the concepts of compressed sensing (CS) leverage the inherent structure of images to retrieve them with far fewer measurements and operate efficiently over a significantly broader spectral range than…
The human visual system contains a hierarchical sequence of modules that take part in visual perception at superordinate, basic, and subordinate categorization levels. During the last decades, various computational models have been proposed…
Optical flow computation with frame-based cameras provides high accuracy but the speed is limited either by the model size of the algorithm or by the frame rate of the camera. This makes it inadequate for high-speed applications. Event…
Video action recognition (VAR) plays crucial roles in various domains such as surveillance, healthcare, and industrial automation, making it highly significant for the society. Consequently, it has long been a research spot in the computer…
Rapid developments in machine vision have led to advances in a variety of industries, from medical image analysis to autonomous systems. These achievements, however, typically necessitate digital neural networks with heavy computational…
How do vision transformers (ViTs) represent and process the world? This paper addresses this long-standing question through the first systematic analysis of 6.6K features across all layers, extracted via sparse autoencoders, and by…
Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image…
3D photography is a new medium that allows viewers to more fully experience a captured moment. In this work, we refer to a 3D photo as one that displays parallax induced by moving the viewpoint (as opposed to a stereo pair with a fixed…
After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and…
Estimating neural radiance fields (NeRFs) from "ideal" images has been extensively studied in the computer vision community. Most approaches assume optimal illumination and slow camera motion. These assumptions are often violated in robotic…
Visual teach-and-repeat (VT&R) navigation enables robots to autonomously traverse previously demonstrated paths using visual feedback. We present a novel event-camera-based VT\&R system. Our system formulates event-stream matching as…