Session 7 Overview: Imagers and Range Sensors
Food Chemistry(2021)SCI 1区
MIT Lincoln Laboratory | TSMC | ST Microelectronics
Abstract
This session covers a wide variety of imagers and range sensors for different applications. For imagers, innovations are reported achieving smaller pixel pitch, higher frame rate or increased on-board intelligence. For ranging, improved SPAD and MEMS based LIDAR are presented and improved depth sensing is achieved. The first paper describes a photodiode-based indirect Time-of-Flight (iToF) depth sensor, followed by three Single Photon Avalanche Diodes (SPAD) based range sensors: a direct Time-of-Flight (dToF) flash LiDAR, a LiDAR system using MEMS mirrors for scanning, and a flash LiDAR with smaller pitch and advanced process node. The next paper presents a SPAD-based photon-counting imager to eliminate the SNR dip problem in photodiode-based high-dynamic-range imagers, followed by a conventional color imager with high resolution, larger pixels, and low noise for digital cameras. The last three papers describe a programmable convolutional imager with near-sensor processing for embedded computer vision applications, a large-format imager for computational imaging with adaptive dynamic range control, and a conventional color imager with high resolution and smaller pixels for smartphone and mobile applications.
MoreTranslated text
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
GPU is busy, summary generation fails
Rerequest