Solving Vision Tasks with Simple Photoreceptors Instead of Cameras

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Atanov, Andrei, Fu, Jiawei, Singh, Rishubh, Yu, Isabella, Spielberg, Andrew, Zamir, Amir
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929388241551360
author Atanov, Andrei
Fu, Jiawei
Singh, Rishubh
Yu, Isabella
Spielberg, Andrew
Zamir, Amir
author_facet Atanov, Andrei
Fu, Jiawei
Singh, Rishubh
Yu, Isabella
Spielberg, Andrew
Zamir, Amir
contents A de facto standard in solving computer vision problems is to use a common high-resolution camera and choose its placement on an agent (i.e., position and orientation) based on human intuition. On the other hand, extremely simple and well-designed visual sensors found throughout nature allow many organisms to perform diverse, complex behaviors. In this work, motivated by these examples, we raise the following questions: 1. How effective simple visual sensors are in solving vision tasks? 2. What role does their design play in their effectiveness? We explore simple sensors with resolutions as low as one-by-one pixel, representing a single photoreceptor First, we demonstrate that just a few photoreceptors can be enough to solve many tasks, such as visual navigation and continuous control, reasonably well, with performance comparable to that of a high-resolution camera. Second, we show that the design of these simple visual sensors plays a crucial role in their ability to provide useful information and successfully solve these tasks. To find a well-performing design, we present a computational design optimization algorithm and evaluate its effectiveness across different tasks and domains, showing promising results. Finally, we perform a human survey to evaluate the effectiveness of intuitive designs devised manually by humans, showing that the computationally found design is among the best designs in most cases.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11769
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Solving Vision Tasks with Simple Photoreceptors Instead of Cameras
Atanov, Andrei
Fu, Jiawei
Singh, Rishubh
Yu, Isabella
Spielberg, Andrew
Zamir, Amir
Computer Vision and Pattern Recognition
A de facto standard in solving computer vision problems is to use a common high-resolution camera and choose its placement on an agent (i.e., position and orientation) based on human intuition. On the other hand, extremely simple and well-designed visual sensors found throughout nature allow many organisms to perform diverse, complex behaviors. In this work, motivated by these examples, we raise the following questions: 1. How effective simple visual sensors are in solving vision tasks? 2. What role does their design play in their effectiveness? We explore simple sensors with resolutions as low as one-by-one pixel, representing a single photoreceptor First, we demonstrate that just a few photoreceptors can be enough to solve many tasks, such as visual navigation and continuous control, reasonably well, with performance comparable to that of a high-resolution camera. Second, we show that the design of these simple visual sensors plays a crucial role in their ability to provide useful information and successfully solve these tasks. To find a well-performing design, we present a computational design optimization algorithm and evaluate its effectiveness across different tasks and domains, showing promising results. Finally, we perform a human survey to evaluate the effectiveness of intuitive designs devised manually by humans, showing that the computationally found design is among the best designs in most cases.
title Solving Vision Tasks with Simple Photoreceptors Instead of Cameras
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.11769