UW-Madison researchers have created methods that enable photon data captured by single-photon detectors, called single-photon avalanche diodes (SPADs), to emulate a wide range of imaging modalities su...
Learn More

UW-Madison researchers developed a novel Time of Flight (ToF) imaging method for dynamic scenes, with the goal of simultaneously estimating 3D geometry, intensity, and 3D motion using a single indirec...
Learn More

UW researchers created a system comprised of single-photon detectors, such as single-photon avalanche diodes (SPADs), along with high-speed projectors that use digital micromirror devices (DMDs) for d...
Learn More

UW-Madison researchers have created computationally light-weight phase-based techniques for low-level vision tasks such as edge detection and motion estimation, which extract scene information directl...
Learn More

UW researchers have developed a novel technique that compensates for motion between high-noise frames using a recurrent convolutional neural network. Existing work uses convolutional neural networks (...
Learn More

UW-Madison researchers and collaborators have created a computational imaging framework called photon inhibition to make single-photon cameras (SPCs) energy efficient. Photon inhibition strategically ...
Learn More

UW-Madison researchers have created generalized event cameras that use event streams to inherently preserve scene intensity without added hardware complexity. These generalized event cameras use an in...
Learn More

UW-Madison researchers have created a method capable of estimating extreme scene motion under challenging conditions, such as low light or high dynamic range, from a sequence of high-speed image frame...
Learn More

UW-Madison researchers have developed a photon processing method that enables reliable scene property estimation over a wide range of operating conditions while requiring no training and remaining agn...
Learn More

UW-Madison researchers have created an event neural network system and associated methods, comprising a family of neural networks in which neurons transmit (thereby triggering downstream computation) ...
Learn More

UW researchers have developed a system for high dynamic range imaging using single-photon and conventional image sensor data. This uses a learning-based, sensor-fusion approach to achieve the extreme ...
Learn More

UW-Madison researchers have developed a method that dynamically changes exposure times on a per pixel basis in response to changes in the scene. The method relies on taking a series of images, then (o...
Learn More

UW-Madison researchers have a computer vision method utilizing spiking neural networks that provides accuracy but does not trade-off latency or power consumption. In recent years, improvements in comp...
Learn More

In accordance with some embodiments, systems, methods and media for encoding and decoding signals used in time-of-flight imaging are provided. In some embodiments, a method for estimating the depth of...
Learn More

A monitoring system may include an input port, an output port, and a controller in communication with the input port and the output port. The input port may receive video from an image capturing devic...
Learn More

A monitoring system or tracking system may include an input port and a controller in communication with the input port. The input port may receive video from an image capturing device. The image captu...
Learn More

In accordance with some embodiments, systems, methods and media for encoding and decoding signals used in time-of-flight imaging are provided. In some embodiments, a method for estimating the depth of...
Learn More

A monitoring system or tracking system may include an input port and a controller in communication with the input port. The input port may receive video from one or more image capturing devices. The i...
Learn More

In accordance with some embodiments, systems, methods and media for encoding structured light imaging patterns and estimating depths in a scene are provided. In some embodiments, a system for estimati...
Learn More

In accordance with some embodiments, methods, systems, and media for detecting the presence of are provided. In some embodiments, a method of detecting an analyte is provided, the method comprising: c...
Learn More

A system and method for automatically generating split screen for a video of a dynamic scene is disclosed. The system generates the split screen by (a) obtaining the video of the dynamic scene, (b) de...
Learn More

In accordance with some aspects, systems, methods and media for hierarchical progressive point cloud rendering are provided. In some aspects, a method for point cloud rendering is provided, the method...
Learn More

An architecture for training the weights of artificial neural networks provides a global constrainer modifying the neuron weights in each iteration not only by the back-propagated error but also by a ...
Learn More

In accordance with some embodiments, systems, methods and media for determining object motion in three dimensions using light field image data are provided. In some embodiments, a system for three dim...
Learn More

A neural net processor provides twin processing paths trainable using different moments of the input data, one moment providing a proxy for uncertainty. Subsequent operation of the trained neural net ...
Learn More