Review of optical pre-sensor computing

Обзор оптических вычислений до сенсора
Zheng Huang, Conghe Wang, Wanxin Shi, Shukai Wu, Yutong He, Yuting Li, Caihua Zhang, Hongwei Chen
2026-07-15

free-space optical operatorsmachine visionnonlinear optical activationoptical neural networksoptical pre-sensor computing
Fueled by the rapid progress of artificial intelligence, machine vision has evolved rapidly in recent years. However, current architectures still rely on cascaded imaging, sensing, transmission and processing stages, leading to substantial data movement, energy consumption and latency. Recent efforts to alleviate these bottlenecks have shifted computation progressively closer to the data source, from backend processors to near-sensor and in-sensor computing units. Optical pre-sensor computing extends this trend to an earlier stage by embedding computation directly into optical propagation before photodetection. It enables task-relevant visual information to be extracted in the optical domain, reducing redundant data acquisition and easing subsequent electronic processing. Benefiting from the intrinsic speed, bandwidth and parallelism of light, this emerging paradigm offers a promising route toward efficient front-end visual information processing. This paper provides a comprehensive review of recent progress in optical pre-sensor computing. Its system architectures and implementation frameworks are first outlined. Advances in free-space optical operators, optical neural networks, and nonlinear optical activation mechanisms are then summarized. Finally, key challenges and opportunities for visual perception in physical AI are discussed, and future directions for optical pre-sensor computing in next-generation machine vision systems are highlighted, with particular emphasis on low-power consumption, high-level integration, and reconfigurable architectures.
1
Conventional machine-vision pipelines incur substantial data movement, energy consumption, and latency because imaging, sensing, transmission, and processing remain cascaded.
2
Key future priorities are low-power operation, high-level integration, and reconfigurable architectures for next-generation machine vision and physical AI.
3
Optical pre-sensor computing embeds task-relevant computation into optical propagation before photodetection, reducing redundant data acquisition and subsequent electronic processing.
4
Recent advances include free-space optical operators, optical neural networks, and nonlinear optical activation mechanisms, supported by diverse system architectures and implementation frameworks.
5
The paradigm exploits light’s intrinsic speed, bandwidth, and parallelism for efficient front-end visual information processing.

optical pre-sensor computing systems for front-end visual information processing

the architectures, implementation frameworks, optical operators, neural-network and nonlinear activation mechanisms, and efficiency challenges of extracting task-relevant visual information before photodetection

Publication Details
Publication Date
2026-07-15
Journal
Publisher
ISSN
Cited by
5
Access Type
Author Information
Authors
Zheng Huang
Conghe Wang
Wanxin Shi
Shukai Wu
Yutong He
Yuting Li
Caihua Zhang
Hongwei Chen
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%