← Back to all news
arXiv Computer Vision By Jiabao Wang, Wenjian Liu, Yaoming Cai, Gengyu Zhang, Boyan Zhao, Zijia Zhang, Yao Ding, Xiaobo Liu

RoES: Rotational Equivariant Selective-frequency Fusion for Multimodal Images

Read the original on arXiv Computer Vision →

RoES is a Rotational Equivariant Selective-frequency fusion network that dynamically separates low- and high-frequency components of infrared-visible images. It uses a trainable rotation-enhanced updater to decouple frequencies, then fuses them with a dual-branch module: a rotation-equivariant Mamba for low-frequency structural dependencies and a polar spectral attention Dual-Fourier block for high-frequency detail refinement. Experiments show RoES outperforms existing methods in fusion quality and downstream object detection, offering a robust multimodal fusion solution.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 4

Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object Detection

The paper introduces FlexibleFusion, a method for infrared-visible object detection that adapts to both complete and missing-modality scenarios. It employs a Modality-Aware Experts Collaboration mechanism to selectively fuse cross-modal or intra-modal pathways, and a Residual Self-Paced Entropic Optimal Transport module to align heterogeneous feature distributions without heavy optimization. Experiments demonstrate consistent performance across various modality configurations.

By Yue Zhao, Hua Yu, Yukun Zhao, Yuzhi Zhang, Maoguo Gong, Xin Mei, Zhuping Hu, Yanchi Li, A. K. Qin
computer-visionefficiencymultimodalsafety
More like this →
arXiv Computer Vision
Sep 25

FoCal: Frequency-Oriented Cross-Modal Interaction and Spectral Calibration for Aerial Visible-Infrared Object Detection

FoCal is a new frequency‑oriented framework for aerial RGB–IR object detection that explicitly models cross‑modal interaction across different frequency components. It introduces a Frequency‑Aware Dual‑Domain Calibration module to consolidate low‑frequency structural cues while preserving high‑frequency modality‑specific details, and a Discrepancy‑Guided Spectral Modulation module that adaptively enhances, preserves, or attenuates the joint spectrum based on confidence‑weighted amplitude discrepancies. Experiments on DroneVehicle, ESCVehicle, and ATR‑UMOD show FoCal achieving high mAP scores (83.5%, 54.8%, 64.6%) with only 3.0 M parameters and 113.6 FPS, demonstrating a strong accuracy–efficiency trade‑off.

By Ben Liang, Chao Sui, Junqi Bai, Yuan Liu, Chunlai Li, Xiubao Sui, Qian Chen
computer-visionmultimodal
More like this →