mlsanityData to 14 Oct 2026

WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection

arXiv 2507.18173 ↗First posted 24 Jul 2025cs.CV cs.MMcited by 14

On the map: State-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing

Abstract (arXiv)

Leveraging the complementary characteristics of visible (RGB) and infrared (IR) imagery offers significant potential for improving object detection. In this paper, we propose WaveMamba, a cross-modality fusion method that efficiently integrates the unique and complementary frequency features of RGB and IR decomposed by Discrete Wavelet Transform (DWT). An improved detection head incorporating the Inverse Discrete Wavelet Transform (IDWT) is also proposed to reduce information loss and produce the final detection results. The core of our approach is the introduction of WaveMamba Fusion Block (WMFB), which facilitates comprehensive fusion across low-/high-frequency sub-bands. Within WMFB, the Low-frequency Mamba Fusion Block (LMFB), built upon the Mamba framework, first performs initial low-frequency feature fusion with channel swapping, followed by deep fusion with an advanced gated attention mechanism for enhanced integration. High-frequency features are enhanced using a strategy that applies an ``absolute maximum" fusion approach. These advancements lead to significant performance gains, with our method surpassing state-of-the-art approaches and achieving average mAP improvements of 4.5% on four benchmarks.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 38 of its 98 references that are in the map. First posted on arXiv 24 Jul 2025.

Builds on

38 of 98 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024DMM: Disparity-guided Multispectral Mamba for Oriented Object Detection in Remote Sensing11 Jul
  2. 2024S4Fusion: Saliency-aware Selective State Space Model for Infrared Visible Image Fusion31 May

Other references · 36

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  3. 2024VMamba: Visual State Space Modelcited by 969
  4. 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 317
  5. 2021LLVIP: A Visible-infrared Paired Dataset for Low-light Visioncited by 231
  6. 2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 223
  7. 2020Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learningcited by 152
  8. 2023Equivariant Multi-Modality Image Fusioncited by 99
  9. 2023Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restorationcited by 88
  10. 2021Cross-Modality Fusion Transformer for Multispectral Object Detectioncited by 86
  11. 2020Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blockscited by 85
  12. 2024Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusioncited by 84
24 more
  1. 2016Multispectral Deep Neural Networks for Pedestrian Detectioncited by 82
  2. 2022Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learningcited by 78
  3. 2023ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detectioncited by 76
  4. 2018Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detectioncited by 74
  5. 2024Wavelet Convolutions for Large Receptive Fieldscited by 74
  6. 2020DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusioncited by 73
  7. 2024Pan-Mamba: Effective pan-sharpening with State Space Modelcited by 73
  8. 2021Multimodal Object Detection via Probabilistic Ensemblingcited by 68
  9. 2023C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detectioncited by 58
  10. 2022Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detectioncited by 50
  11. 2021Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagerycited by 45
  12. 2023Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Taskscited by 41
  13. 2019Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagerycited by 38
  14. 2022Multi-stage image denoising with the wavelet transformcited by 37
  15. 2023Learning a Graph Neural Network with Cross Modality Interaction for Image Fusioncited by 28
  16. 2024DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusioncited by 28
  17. 2021SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurringcited by 26
  18. 2024Learning Adaptive Fusion Bank for Multi-modal Salient Object Detectioncited by 19
  19. 2024Removal then Selection: A Coarse-to-Fine Fusion Perspective for RGB-Infrared Object Detectioncited by 16
  20. 2024TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mambacited by 15
  21. 2023Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detectioncited by 12
  22. 2024TSJNet: A Multi-modality Target and Semantic Awareness Joint-driven Image Fusion Networkcited by 10
  23. 2024MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detectioncited by 6
  24. 2021Image restoration quality assessment based on regional differential information entropycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 11.

14 papers.

Sort:

By area:

  1. 2026SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detectioncited by 4
  2. 2025AlignFreeNet: Is Cross-Modal Pre-Alignment Necessary? An End-to-End Alignment-Free Lightweight Network for Visible-Infrared Object Detectioncited by 1
  3. 2025Representation Space Constrained Learning with Modality Decoupling for Multimodal Object Detectioncited by 1
  4. 2026Bridging the RGB-IR Gap: Consensus and Discrepancy Modeling for Text-Guided Multispectral Detectioncited by 1
  5. 2026GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perceptioncited by 1
  6. 2025MM-DETR: An Efficient Multimodal Detection Transformer with Mamba-Driven Dual-Granularity Fusion and Frequency-Aware Modality Adapterscited by 0
  7. 2026InfraNet: Quality-Aware RGB Guidance for Efficient Infrared Object Detectioncited by 0
  8. 2026Geometric Causal Modelscited by 0
  9. 2026DRPFNet: Dual-domain Residual Progressive Fusion Network for RGB-Thermal Object Detectioncited by 0
  10. 2026RegisterBridgeMM: A Register-Centric Framework for RGB-Infrared Object Detectioncited by 0
  11. 2026InterPruner: Interactive Structured Pruning via Taylor-Implicit Criterion and Language-Prior Modulator for Multimodal Object Detectioncited by 0
  12. 2026Aligned Radiometric RGB-Thermal Fusion for UAV Facade Anomaly Screeningcited by 0
2 more
  1. 2026FoCal: Frequency-Oriented Cross-Modal Interaction and Spectral Calibration for Aerial Visible-Infrared Object Detectioncited by 0
  2. 2026SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Exploring State Space Model in Wavelet Domain: An Infrared and Visible Image Fusion Network via Wavelet Transform and State Space Model
  2. 2024MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object Detection
  3. 2025Multispectral Detection Transformer with Infrared-Centric Feature Fusion
  4. 2024Fusion-Mamba for Cross-modality Object Detection
  5. 2025HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection
  6. 2024IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model
  7. 2024WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image Classification
  8. 2025LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object Detection