Beyond Unfolding: 60x Faster One-Stage Unmixing for Closely-Spaced Infrared Small Targets

2026-07-17

AI Summary

This work addresses the challenge of resolving densely packed infrared small targets whose energy distributions overlap due to optical diffraction limits and long-range imaging, rendering them difficult to distinguish. To tackle this issue, the authors propose FOCUS—a lightweight, single-stage infrared small target unmixing framework. Departing from conventional deep unfolding paradigms, FOCUS leverages the structural similarity between image super-resolution and unmixing degradation models to enable a paradigm shift from super-resolution to unmixing. It incorporates a flux conservation constraint to mitigate signal attenuation caused by sparse regularization and employs a coarse-to-fine, single-pass mapping strategy. Implemented as an end-to-end architecture with a tailored unmixing loss function and evaluation metrics, FOCUS achieves state-of-the-art or comparable performance in both localization and unmixing accuracy while offering a 60-fold speedup in inference time.

Abstract

Due to the optical diffraction limit and long imaging distances, Closely-Spaced Infrared Small Targets (CSIST) typically exhibit energy overlap, manifesting as indistinguishable blobs in infrared images. This ambiguity invalidates the one-to-one mapping assumption of traditional detection, thereby necessitating a paradigm shift towards CSIST Unmixing, which decomposes these blobs into discrete sub-targets. However, the dominant paradigm deep unfolding networks are shackled by the high latency and structural inflexibility intrinsic to their repetitively iterative architecture. To this end, we propose the Fast One-stage CSIST Unmixing Scheme (FOCUS), a one-stage lightweight paradigm which demonstrates that deep unfolding is not necessary. Motivated by the key observation that image super-resolution (SR) and CSIST Unmixing share an isomorphic degradation model, our insight is that it is possible to achieve a paradigm shift from image SR to CSIST Unmixing via completely transforming the label space, loss functions, and evaluation criteria. Specifically, to avoid entangling geometric recovery with artifact suppression, FOCUS adopts a single pass mapping with an internal coarse-to-fine flow that progressively refines target localization from coarse spatial distributions to finer sub-pixel precision. While sparsity regularization suppresses background clutter, it also attenuates target intensities. To compensate for this attenuation of valid signals, flux conservation is introduced as a competing constraint that restores signal energy back to target centers. To the best of our knowledge, this work is the first attempt to address this task via a lightweight one-stage framework without the DUN paradigm. Experiments demonstrate that our method matches or surpasses the state-of-the-art unfolding approaches in both localization and unmixing accuracy, while boosting the inference speed by 60x.

Problem

• Closely-Spaced Infrared Small Targets
• CSIST Unmixing
• energy overlap
• infrared image ambiguity
• target decomposition

Innovation

• CSIST Unmixing
• One-stage Framework
• Flux Conservation
• Deep Unfolding Avoidance
• Coarse-to-fine Refinement