LDFE: Laplacian Decoupled Feature Enhancement Block for Dual-Stream CNN-based RGB-IR Object Detection

• URL: http://arxiv.org/abs/2607.08076v1
• Date: Thu, 09 Jul 2026 03:11:00 GMT
• Title: LDFE: Laplacian Decoupled Feature Enhancement Block for Dual-Stream CNN-based RGB-IR Object Detection
• Abstract summary: Existing methods prefer dual-stream CNN backbones built upon YOLO for feature extraction.<n>We introduce the Laplacian Decoupled Feature Enhancement block (LDFE) to fuse features from different stages of the dual-stream CNN backbone.
• Score: 42.233702113689695
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The complementary information between RGB and IR images can significantly enhance object detection performance under extreme conditions. Existing methods prefer dual-stream CNN backbones built upon YOLO for feature extraction and focus on the design of feature fusion. In this paper, we introduce the Laplacian Decoupled Feature Enhancement block (LDFE) to fuse features from different stages of the dual-stream CNN backbone. By design, LDFE simultaneously considers the characteristics of modalities and structures for feature fusion by employing global-local decomposition, denoising, fusion, and reconstruction, sequentially. The LDFE first separates features into global and local components based on Laplacian Pyramid, and then performs denoising and fusion based on Global State Space Enhancement module (GS2E) and Local Convolutional Correlation Enhancement module (LC2E) separately. Specifically, the GS2E conducts a two-branch architecture for the main and auxiliary modalities. It dynamically suppresses noise in the main modality through cross-modal attention derived from the auxiliary modality, while employing a State Space Model to capture long-range dependencies within the global feature representations of the main modality. To obtain bidirectional interaction, the two modalities systematically alternate their main/auxiliary roles. Moreover, the LC2E suppresses noise in local features and leverages spatial and channel dimension along with triple convolution to extract fine-grained details for fusion. These innovative designs achieve a significant performance improvement, with mAP surpassing the SOTA methods 6.2%, 3.7%, 4.7%, 2.3%, 4.1% and 2.0% on M3FD, DroneVehicle, LLVIP, FLIR-Aligned, KAIST and VEDAI datasets,respectively.

Related papers

• DRPFNet: Dual-domain Residual Progressive Fusion Network for RGB-Thermal Object Detection [13.47934602159213]
  RGB-thermal (RGB-T) object detection aims to fuse complementary information from visible and thermal modalities to achieve robust detection under varying illumination and weather conditions.<n>Current methods typically employ attention mechanisms or transformers to perform cross-modal fusion independently at each feature scale.<n>We propose DRPFNet, a Dual-domain Residual Progressive Fusion Network that constructs a unified information flow optimization system from three synergistic levels:structure, feature, and enhancement.
  arXiv  Detail & Related papers  (2026-08-04T09:20:31Z)
• DIFF-MF: A Difference-Driven Channel-Spatial State Space Model for Multi-Modal Image Fusion [51.07069814578009]
  Multi-modal image fusion aims to integrate complementary information from multiple source images to produce high-quality fused images with enriched content.<n>We propose DIFF-MF, a novel difference-driven channel-spatial state space model for multi-modal image fusion.<n>Our method outperforms existing approaches in both visual quality and quantitative evaluation.
  arXiv  Detail & Related papers  (2026-01-09T05:26:54Z)
• Pyramidal Adaptive Cross-Gating for Multimodal Detection [0.0]
  PACGNet is an architecture designed to perform deep fusion within the backbone.<n>The P module reconstructs the feature hierarchy via a progressive hierarchical gating mechanism.<n>Our PACGNet sets a new state-of-the-art benchmark, with mAP50 scores reaching 81.7% and 82.1% respectively.
  arXiv  Detail & Related papers  (2025-12-20T09:32:18Z)
• Residual Prior-driven Frequency-aware Network for Image Fusion [6.90874640835234]
  Image fusion aims to integrate complementary information across modalities to generate high-quality fused images.<n>We propose a Residual Prior-driven Frequency-aware Network, termed as RPFNet.
  arXiv  Detail & Related papers  (2025-07-09T10:48:00Z)
• PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification [49.37555541088792]
  Phase-Amplitude Decoupling (PAD) is a frequency-aware framework that separates phase (modality-shared) and amplitude (modality-complementary) components.<n>This work establishes a new paradigm for physics-aware multi-modal fusion in remote sensing.
  arXiv  Detail & Related papers  (2025-04-27T07:21:42Z)
• MS-Occ: Multi-Stage LiDAR-Camera Fusion for 3D Semantic Occupancy Prediction [15.656771219382076]
  MS-Occ is a novel multi-stage LiDAR-camera fusion framework.<n>It integrates LiDAR's geometric fidelity with camera-based semantic richness.<n>Experiments show MS-Occ achieves an Intersection over Union (IoU) of 32.1% and a mean IoU (mIoU) of 25.3%.
  arXiv  Detail & Related papers  (2025-04-22T13:33:26Z)
• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [92.4205087439928]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.<n>We propose the Self-supervised Transfer (PST) and the FrequencyDe-coupled Fusion module (FreDF)<n>PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models, effectively mitigating data scarcity.<n>FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.<n>This combined approach enables FUSE to construct a universal image-event that only requires lightweight decoder adaptation for target datasets.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• Dual Mutual Learning Network with Global-local Awareness for RGB-D Salient Object Detection [10.353412441955436]
  We propose the GL-DMNet, a novel dual mutual learning network with global-local awareness.<n>We present a position mutual fusion module and a channel mutual fusion module to exploit the interdependencies among different modalities.<n>Our proposed GL-DMNet performs better than 24 RGB-D SOD methods, achieving an average improvement of 3%.
  arXiv  Detail & Related papers  (2025-01-03T05:37:54Z)
• PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection [59.355022416218624]
  integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. We propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN) PVAFN uses a multi-pooling strategy to integrate both multi-scale and region-specific information effectively.
  arXiv  Detail & Related papers  (2024-08-26T19:43:01Z)
• CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion [138.40422469153145]
  We propose a novel Correlation-Driven feature Decomposition Fusion (CDDFuse) network. We show that CDDFuse achieves promising results in multiple fusion tasks, including infrared-visible image fusion and medical image fusion.
  arXiv  Detail & Related papers  (2022-11-26T02:40:28Z)
• RGB-D Salient Object Detection with Cross-Modality Modulation and Selection [126.4462739820643]
  We present an effective method to progressively integrate and refine the cross-modality complementarities for RGB-D salient object detection (SOD) The proposed network mainly solves two challenging issues: 1) how to effectively integrate the complementary information from RGB image and its corresponding depth map, and 2) how to adaptively select more saliency-related features.
  arXiv  Detail & Related papers  (2020-07-14T14:22:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.