Compute-First Optical Detection for Noise-Resilient Visual Perception

Download:

• Paper

Abstract:

During machine visual perception, the optical signal from a scene is transferred into the electronic domain by detectors in the form of image data, which are then processed for the extraction of visual information. In noisy environments, such as a thermal imaging system, however, the neural performance faces a significant bottleneck due to the inherent degradation of data quality upon noisy detection. Here, we propose a concept of optical signal processing before detection to address this issue. We demonstrate that spatially redistributing optical signals through a properly designed linear transformer can enhance the detection noise resilience of visual perception, as benchmarked with MNIST classification. A quantitative analysis of the relationship between signal concentration and noise robustness supports our idea with its practical implementation in an incoherent imaging system. This compute-first detection scheme can advance infrared machine vision technologies for industrial and defense applications.

Citation

J. Kim et al., “Compute-First Optical Detection for Noise-Resilient Visual Perception.” ACS Photonics 12: 1137-1145 (2025). https://doi.org/10.1021/acsphotonics.4c02284.

@article{Kim2025_noise,
    title = {Compute-First Optical Detection for Noise-Resilient Visual Perception},
    volume = {12},
    ISSN = {2330-4022},
    url = {http://dx.doi.org/10.1021/acsphotonics.4c02284},
    DOI = {10.1021/acsphotonics.4c02284},
    number = {2},
    journal = {ACS Photonics},
    publisher = {American Chemical Society (ACS)},
    author = {Kim,  Jungmin and Yu,  Nanfang and Yu,  Zongfu},
    year = {2025},
    month = feb,
    pages = {1137–1145}
}

Related material