Seeing the Unseen: Camouflaged Object Detection Beyond the Visible Spectrum
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors explore how to better find objects that blend into their surroundings, called camouflaged objects, by using multispectral images instead of just regular RGB images. Multispectral images capture many ranges of light, providing more detailed information than standard photos. They developed a new method called MSFormer that uses these detailed images to predict where camouflaged objects are. Their experiments show that this method works better than previous ones that only used normal images. The authors also explain why using multispectral data helps with this tricky detection task.
Camouflaged Object DetectionMultispectral ImagingRGB ImageryBinary MaskLow-Visibility ScenariosSpectral SignaturesEnd-to-End FrameworkImage Segmentation
Authors
Avi Gupta, Trasha Gupta
Abstract
Recent advances in camouflaged object detection (COD) have led to substantial progress in challenging low-visibility scenarios, with pioneering studies demonstrating notable success in localizing objects in camouflaged scenes. Despite these achievements, existing approaches predominantly rely on conventional three-channel RGB imagery, thereby constraining the available visual information to a limited spectral range. Multispectral images offer a wide range of information about a scene by capturing fine-grained spectral signatures. Hence, by leveraging multispectral images for COD, we introduce a novel approach to detect camouflaged objects from the corresponding multispectral inputs. In particular, we propose an end-to-end framework, \textbf{\textit{MSFormer}}, that takes a multispectral camouflaged image as input and predicts a binary mask for it. Additionally, we also provide empirical justification for integrating multispectral bands for this complex low-vision task. Our extensive experiments demonstrate the effectiveness of our method, which outperforms existing methods.