DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ni, Kang, Zou, Minrui, Li, Yuxuan, Li, Xiang, Guo, Kehua, Cheng, Ming-Ming, Dai, Yimian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909735642464256
author Ni, Kang
Zou, Minrui
Li, Yuxuan
Li, Xiang
Guo, Kehua
Cheng, Ming-Ming
Dai, Yimian
author_facet Ni, Kang
Zou, Minrui
Li, Yuxuan
Li, Xiang
Guo, Kehua
Cheng, Ming-Ming
Dai, Yimian
contents One of the primary challenges in Synthetic Aperture Radar (SAR) object detection lies in the pervasive influence of coherent noise. As a common practice, most existing methods, whether handcrafted approaches or deep learning-based methods, employ the analysis or enhancement of object spatial-domain characteristics to achieve implicit denoising. In this paper, we propose DenoDet V2, which explores a completely novel and different perspective to deconstruct and modulate the features in the transform domain via a carefully designed attention architecture. Compared to DenoDet V1, DenoDet V2 is a major advancement that exploits the complementary nature of amplitude and phase information through a band-wise mutual modulation mechanism, which enables a reciprocal enhancement between phase and amplitude spectra. Extensive experiments on various SAR datasets demonstrate the state-of-the-art performance of DenoDet V2. Notably, DenoDet V2 achieves a significant 0.8\% improvement on SARDet-100K dataset compared to DenoDet V1, while reducing the model complexity by half. The code is available at https://github.com/GrokCV/GrokSAR.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09392
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection
Ni, Kang
Zou, Minrui
Li, Yuxuan
Li, Xiang
Guo, Kehua
Cheng, Ming-Ming
Dai, Yimian
Computer Vision and Pattern Recognition
One of the primary challenges in Synthetic Aperture Radar (SAR) object detection lies in the pervasive influence of coherent noise. As a common practice, most existing methods, whether handcrafted approaches or deep learning-based methods, employ the analysis or enhancement of object spatial-domain characteristics to achieve implicit denoising. In this paper, we propose DenoDet V2, which explores a completely novel and different perspective to deconstruct and modulate the features in the transform domain via a carefully designed attention architecture. Compared to DenoDet V1, DenoDet V2 is a major advancement that exploits the complementary nature of amplitude and phase information through a band-wise mutual modulation mechanism, which enables a reciprocal enhancement between phase and amplitude spectra. Extensive experiments on various SAR datasets demonstrate the state-of-the-art performance of DenoDet V2. Notably, DenoDet V2 achieves a significant 0.8\% improvement on SARDet-100K dataset compared to DenoDet V1, while reducing the model complexity by half. The code is available at https://github.com/GrokCV/GrokSAR.
title DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.09392