Videos du jour for Nov 14, 2022

Graphene Flagship (https://graphene-flagship.eu/) spearhead project AUTOVISION is developing a new high-resolution image sensor for autonomous vehicles, which can detect obstacles and road curvature even in extreme and difficult driving conditions.

 

 

SPAD and CIS camera fusion for high resolution high dynamic range passive imaging (IEEE/CVF WACV 2022) Authors: Yuhao Liu (University of Wisconsin-Madison)*; Felipe Gutierrez-Barragan (University of Wisconsin-Madison); Atul N Ingle (University of Wisconsin-Madison); Mohit Gupta ("University of Wisconsin-Madison, USA "); Andreas Velten (University of Wisconsin - Madison) Description: Reconstruction of high-resolution extreme dynamic range images from a small number of low dynamic range (LDR) images is crucial for many computer vision applications. Current high dynamic range (HDR) cameras based on CMOS image sensor technology rely on multiexposure bracketing which suffers from motion artifacts and signal-to-noise (SNR) dip artifacts in extreme dynamic range scenes. Recently, single-photon cameras (SPCs) have been shown to achieve orders of magnitude higher dynamic range for passive imaging than conventional CMOS sensors. SPCs are becoming increasingly available commercially, even in some consumer devices. Unfortunately, current SPCs suffer from low spatial resolution. To overcome the limitations of CMOS and SPC sensors, we propose a learning-based CMOS-SPC fusion method to recover high-resolution extreme dynamic range images. We compare the performance of our method against various traditional and state-of-the-art baselines using both synthetic and experimental data. Our method outperforms these baselines, both in terms of visual quality and quantitative metrics.

System Semiconductor Image Sensor Explained | 'All About Semiconductor' by Samsung Electronics

tinyML neuromorphic engineering discussion forum:

Neuromorphic Event-based Vision
Christoph POSCH
CTO
PROPHESEE

New Architecture for Visual AI, Oculi Technology Enables Edge Solutions At The Speed Of Machines With The Efficiency of Biology
Charbel RIZK,
Founder CEO
Oculi Inc.

Roman Genov, University of Toronto
Fast Field-Programmable Coded Image Sensors for Versatile Low-Cost Computational Imaging Presented through the Chalk Talks series of the Institute for Neural Computation (UC San Diego)
08/05/22