Reinterpretable cameras are defined by their post-processing capabilities that exceed traditional imaging. We present “SoDaCam”…
Research Categories
All Projects
Underlying many structured light systems, especially those based on laser scanning, is a simple vision…
Single-photon 3D cameras can record the time-of-arrival of billions of photons per second with picosecond…
Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy…
Visual codes such as QR codes are widely used in several applications for conveying information…
Single-photon sensors measure light signals at the finest possible resolution — individual photons. These sensors…
Scene reconstruction in the presence of high-speed motion and low illumination is important in many…
Megapixel single-photon avalanche diode (SPAD) arrays have been developed recently, opening up the possibility of…
We provide methods which recover planar scene geometry by utilizing the transient histograms captured by a class…
Image sensors capable of capturing individual photons have made tremendous technological progress in recent years. …
Motion estimation is important not only for human vision systems, but also for machine vision….
In many emerging computer vision applications, it is critical to adhere to stringent latency and…
Single-photon avalanche diodes (SPADs) are novel image sensors that record the arrival of individual photons…
Artificial neural networks are the state of the art in visual recognition. Many of these…
Visual codes such as QR codes provide a low-cost and convenient communication channel between physical…
Time-resolved image sensors that capture light at pico-to-nanosecond timescales were once limited to niche applications…
Single-photon avalanche diodes (SPADs) are an emerging pixel technology for time-of-flight (ToF) 3D cameras that…
Scene inference under low-light is a challenging problem due to severe noise in the captured…
Structured light 3D imaging systems have inherent tradeoffs balancing the precision of the 3D scan…
Physical adversarial examples for camera-based computer vision have so far been achieved through visible artifacts…
Reconstruction of high-resolution extreme dynamic range images from a small number of low dynamic range…
Single-pixel distance sensors are a low-power, low-cost option for distance ranging, and are often attached…
Scene understanding under low-light conditions is a challenging problem. This is due to the small…
Indirect Time-of-Flight (iToF) cameras are a promising depth sensing technology. However, they are prone to…
For several vision and robotics applications, 3D geometry of man-made environments such as indoor scenes…
We present inertial safety maps (ISM), a novel scene representation designed for fast detection of…
Digital camera pixels capture images by converting incident light energy into an analog electrical current,…
Single-photon avalanche diodes (SPADs) are an emerging sensor technology capable of detecting individual incident photons,…
We propose a novel imaging method for near-complete, surround, 3D reconstruction of geometrically complex objects,…
Structured light (SL) 3D imaging face a trade-off between acquisition and computational complexity. Multi-shot SL…