Dual-Integrated Low-Latency Single-Lens Infrared Computational Imaging for Object Detection

TL;DR

The paper introduces PDI-Net, a physics-aware, low-latency infrared imaging framework that integrates reconstruction and detection, significantly reducing inference time and system weight for real-time object detection.

Contribution

It proposes a novel dual-integrated network with optical priors and a physics-informed pipeline, enabling efficient infrared object detection on resource-limited platforms.

Findings

Reduces inference time by 84.06% compared to baseline methods.

Improves detection accuracy (mAP) by 5.07% on the M3FD benchmark.

Decreases system weight by approximately 50% with a single-lens design.

Abstract

Computational imaging enables compact infrared systems, but deep-learning pipelines that combine image reconstruction and object detection often introduce substantial inference latency. Most existing acceleration strategies compress the reconstruction network while overlooking physical priors from the optical path, leaving a trade-off between accuracy and speed. We present Physics-aware Dual-Integrated Network (PDI-Net), a low-latency framework that integrates infrared reconstruction with object detection and further embeds optical priors into the learning process. PDI-Net uses a supervised U-Net during training, while a semi-U-Net encoder shares features directly with a YOLO-based detector during inference, avoiding full image reconstruction. To bridge the gap between fidelity-oriented reconstruction features and detection-oriented semantics, we introduce a physics-aware large-small bridge (PALS-Bridge), which uses field-dependent point spread function priors to adaptively modulate multiscale convolutional branches. A physics-informed optical degradation simulation pipeline is also developed for training and validation. The method is deployed on a single-lens infrared camera, reducing system weight by about 50% compared with traditional multi-lens designs. On the M3FD benchmark under low-SNR conditions, PDI-Net reduces inference time by 84.06% compared with the Rec+Det with pruning strategy while improving mAP@0.5:0.95 by 5.07%. These results demonstrate compact, low-latency computational infrared imaging for real-time object detection on resource-constrained platforms.