yuanmaoxun / Awesome-RGBT-Fusion

A collection of deep learning based RGB-T-Fusion methods, codes, and datasets. The main directions involved are Multispectral Pedestrian Detection, RGB-T Aerial Object Detection, RGB-T Semantic Segmentation, RGB-T Crowd Counting, RGB-T Fusion Tracking.

Awesome RGB-T Fusion

A collection of deep learning based RGB-T-Fusion methods, codes, and datasets.
The main directions involved are Multispectral Pedestrian Detection, RGB-T Vehicle Detection, RGB-T Crowd Counting, RGB-T Fusion Tracking.
Feel free to star and fork! We will continue to update this repository!

Contents

1. Multispectral Pedestrian Detection
2. RGB-T Vehicle Detection
3. RGB-T Crowd Counting
4. RGB-T Salient Object Detection
5. RGB-T Fusion Tracking

Multispectral Pedestrian Detection

Datasets and Annotations

KAIST dataset, CVC-14 dataset, FLIR dataset, FLIR-aligned dataset, LLVIP dataset, M³FD dataset

• Improved KAIST Testing Annotations provided by Liu et al.Link to download
• Sanitized KAIST Training Annotations provided by Li et al.Link to download
• Improved KAIST Training Annotations provided by Zhang et al.Link to download

Tools

• Evalutaion codes.Link to download
• Annotation: vbb format->xml format.Link to download

Papers

Fusion Architecture

1. ICAFusion: Iterative cross-attention guided feature fusion for multispectral object detection, Pattern Recognition 2024, Shen Jifeng et al. [PDF][Code]
2. Improving RGB-infrared object detection with cascade alignment-guided transformer, Information Fusion 2024, Maoxun Yuan et al. [PDF]
3. Multispectral Object Detection via Cross-Modal Conflict-Aware Learning, ACM MM 2023, Xiao He et al. [PDF]
4. Stabilizing Multispectral Pedestrian Detection with Evidential Hybrid Fusion, TCSVT 2023, Li Qing et al. [PDF]
5. Multimodal Object Detection by Channel Switching and Spatial Attention, CVPRW 2023, Yue Cao et al. [PDF]
6. Multi-Modal Feature Pyramid Transformer for RGB-Infrared Object Detection, TITS 2023, Yaohui Zhu et al. [PDF]
7. Multiscale Cross-modal Homogeneity Enhancement and Confidence-aware Fusion for Multispectral Pedestrian Detection, TMM 2023, Ruimin Li et al. [PDF]
8. HAFNet: Hierarchical Attentive Fusion Network for Multispectral Pedestrian Detection, Remote Sensing 2023, Peiran Peng et al. [PDF]
9. Multimodal Object Detection via Probabilistic Ensembling, ECCV2022, Yi-Ting Chen et al. [PDF]
10. Learning a Dynamic Cross-Modal Network for Multispectral Pedestrian Detection, ACM Multimedia 2022, Jin Xie et al. [PDF]
11. Confidence-aware Fusion using Dempster-Shafer Theory for Multispectral Pedestrian Detection, TMM 2022, Qing Li et al. [PDF]
12. Attention-Guided Multi-modal and Multi-scale Fusion for Multispectral Pedestrian Detection, PRCV 2022, Wei Bao et al. [PDF]
13. Improving RGB-Infrared Pedestrian Detection by Reducing Cross-Modality Redundancy, ICIP2022, Qingwang Wang et al. [PDF]
14. Spatio-contextual deep network-based multimodal pedestrian detection for autonomous driving, IEEE Transactions on Intelligent Transportation Systems, Kinjal Dasgupta et al. [PDF]
15. Adopting the YOLOv4 Architecture for Low-LatencyMultispectral Pedestrian Detection in Autonomous Driving, Sensors 2022, Kamil Roszyk et al. [PDF]
16. Deep Active Learning from Multispectral Data Through Cross-Modality Prediction Inconsistency, ICIP2021, Heng Zhang et al.[PDF]
17. Attention Fusion for One-Stage Multispectral Pedestrian Detection, Sensors 2021, Zhiwei Cao et al. [PDF]
18. Uncertainty-Guided Cross-Modal Learning for Robust Multispectral Pedestrian Detection, IEEE Transactions on Circuits and Systems for Video Technology 2021, Jung Uk Kim et al. [PDF]
19. Deep Cross-modal Representation Learning and Distillation for Illumination-invariant Pedestrian Detection, IEEE Transactions on Circuits and Systems for Video Technology 2021, T. Liu et al. [PDF]
20. Guided Attentive Feature Fusion for Multispectral Pedestrian Detection, WACV 2021, Heng Zhang et al. [PDF]
21. Anchor-free Small-scale Multispectral Pedestrian Detection, BMVC 2020, Alexander Wolpert et al. [PDF][Code]
22. Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks, ICIP 2020, Heng Zhang et al. [PDF]
23. Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems, ECCV 2020, Kailai Zhou et al. [PDF][Code]
24. Anchor-free Small-scale Multispectral Pedestrian Detection, BMVC 2020, Alexander Wolpert et al. [PDF][Code]
25. Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection, ICCV 2019, Lu Zhang et al. [PDF][Code]
26. Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pesdestrian Detecion, ISPRS Journal of Photogrammetry and Remote Sensing 2019, Yanpeng Cao et al.[PDF][Code]
27. Cross-modality interactive attention network for multispectral pedestrian detection, Information Fusion 2019, Lu Zhang et al.[PDF][Code]
28. Pedestrian detection with unsupervised multispectral feature learning using deep neural networks, Information Fusion 2019, Cao, Yanpeng et al.[PDF]
29. Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation, BMVC 2018, Chengyang Li et al.[PDF][Code][Project Link]
30. Unified Multi-spectral Pedestrian Detection Based on Probabilistic Fusion Networks, Pattern Recognition 2018, Kihong Park et al.[PDF]
31. Multispectral Deep Neural Networks for Pedestrian Detection, BMVC 2016, Jingjing Liu et al.[PDF][Code]
32. Multispectral Pedestrian Detection Benchmark Dataset and Baseline, 2015, Soonmin Hwang et al.[PDF][Code]

Pixel-level Fusion for Detection

1. Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion, ICCV 2023, Yiming Sun et al.[PDF]
2. MetaFusion : Infrared and Visible Image Fusion via Meta-Feature Embedding from Object Detection, CVPR 2023, Wenda Zhao et al. [PDF][Code]
3. Locality guided cross-modal feature aggregation and pixel-level fusion for multispectral pedestrian detection, Information Fusion 2022, Yanpeng Cao et al. [PDF]
4. Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection, CVPR 2022, Jinyuan Liu et al.[PDF][Code]
5. DetFusion: A Detection-driven Infrared and Visible Image Fusion Network, ACM Multimedia 2022, Yiming Sun et al. [PDF][Code]

Illumination Aware

1. Illumination-Guided RGBT Object Detection With Inter- and Intra-Modality Fusion, IEEE Transactions on Instrumentation and Measurement 2023, Yan Zhang et al. [PDF]
2. IGT: Illumination-guided RGB-T object detection with transformers, Knowledge-Based Systems 2023, Keyu Chen et al. [PDF]
3. Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery, ECCV 2020, My Kieu et al. [PDF][Code]
4. Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection, Information Fusion 2019, Dayan Guan et al.[PDF][Code]
5. Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection, Pattern Recognition 2018, Chengyang Li et al.[PDF][Code]

Feature Alignment

1. Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detection, TMM 2024, Chao Tian et al. [PDF]
2. Attentive Alignment Network for Multispectral Pedestrian Detection, ACM MM 2023, Nuo Chen et al. [PDF]
3. Towards Versatile Pedestrian Detector with Multisensory-Matching and Multispectral Recalling Memory, AAAI2022, Jung Uk Kim et al. [PDF]
4. Mlpd: Multi-label pedestrian detector in multispectral domain, IEEE Robotics and Automation Letters 2021, Jiwon Kim et al. [PDF]
5. Weakly Aligned Feature Fusion for Multimodal Object Detection, ITNNLS 2021, Lu Zhang et al. [PDF]
6. Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems, ECCV 2020, Kailai Zhou et al. [PDF][Code]
7. Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection, ICCV 2019, Lu Zhang et al. [PDF] [Code]
8. Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation, BMVC 2018, Chengyang Li et al. [PDF] [Code]

Single Modality

1. Towards Versatile Pedestrian Detector with Multisensory-Matching and Multispectral Recalling Memory, AAAI 2022, Kim et al. [PDF]
2. Robust Thermal Infrared Pedestrian Detection By Associating Visible Pedestrian Knowledge, ICASSP 2022, Sungjune Park et al. [PDF]
3. Low-cost Multispectral Scene Analysis with Modality Distillation, Zhang Heng et al. [PDF]
4. Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery, ECCV 2020, My Kieu et al. [PDF][Code]
5. Deep Cross-modal Representation Learning and Distillation for Illumination-invariant Pedestrian Detection, IEEE Transactions on Circuits and Systems for Video Technology 2021, T. Liu et al. [PDF]

Unsupervised Domain Adaptation

1. Unsupervised Domain Adaptation for Multispectral Pedestrian Detection, CVPR 2019 Workshop , Dayan Guan et al. [PDF] [Code]
2. Pedestrian detection with unsupervised multispectral feature learning using deep neural networks, Information Fusion 2019, Y. Cao et al. Information Fusion 2019, [PDF] [Code]
3. Learning crossmodal deep representations for robust pedestrian detection, CVPR 2017, D. Xu et al.[PDF][Code]

RGB-T Vehicle Detection

Datasets

DroneVehicle: partially aligned [link]

VEDAI: strictly aligned [link]

Multispectral Datasets for Detection and Segmentation: with Segmentation annotation [link]

papers

1. ICAFusion: Iterative cross-attention guided feature fusion for multispectral object detection, Pattern Recognition 2024, Shen Jifeng et al. [PDF][Code]
2. Improving RGB-infrared object detection with cascade alignment-guided transformer, Information Fusion 2024, Maoxun Yuan et al. [PDF]
3. Multispectral Object Detection via Cross-Modal Conflict-Aware Learning, ACM MM 2023, Xiao He et al. [PDF][Code]
4. LRAF-Net: Long-Range Attention Fusion Network for Visible–Infrared Object Detection, TNNLS 2023, Haolong Fu et al. [PDF]
5. GF-Detection: Fusion with GAN of Infrared and Visible Images for Vehicle Detection at Nighttime, Remote Sensing 2022, Peng Gao et al. [PDF]
6. Cross-modality attentive feature fusion for object detection in multispectral remote sensing imagery, Pattern Recognition, Qingyun Fang et al. [PDF]
7. Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection, ECCV 2022, Maoxun Yuan et al. [PDF]
8. Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning, TCSVT 2022, Yiming Sun [PDF]
9. Improving RGB-Infrared Object Detection by Reducing Cross-Modality Redundancy, Remote Sensing 2022, Qingwang Wang et al. [PDF]

RGB-T Crowd Counting

Datasets

RGBT-CC[link], DroneCrowd [link]

papers

Domain Adaptation

1. RGB-T Crowd Counting from Drone: A Benchmark and MMCCN Network, ACCV2020, Tao Peng et al. [PDF][Code]

Fusion Architecture

1. CCANet: A Collaborative Cross-modal Attention Network for RGB-D Crowd Counting, TMM2023, Yanbo Liu et al. [PDF]
2. MC3Net: Multimodality Cross-Guided Compensation Coordination Network for RGB-T Crowd Counting, TITS 2023, Wujie Zhou et al. [PDF]
3. RGB-T Multi-Modal Crowd Counting Based on Transformer, BMVC 2022, Zhengyi Liu et al. [PDF]
4. Spatio-channel Attention Blocks for Cross-modal Crowd Counting, ACCV2022, Youjia Zhang et al. [PDF]
5. DEFNet: Dual-Branch Enhanced Feature Fusion Network for RGB-T Crowd Counting, TITS 2022, Zhou, Wujie et al. [PDF]
6. MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Counting, arxiv2022, Pengyu Chen et al. [PDF]
7. Multimodal Crowd Counting with Mutual Attention Transformers, ICME 2022, Wu, Zhengtao et al. [PDF]
8. Conditional RGB-T Fusion for Effective Crowd Counting, ICIP 2022, Esha Pahwa et al. [PDF]
9. Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting, CVPR2021, Lingbo Liu et al. [PDF][Code]

RGB-T Salient Object Detection

Datasets

VT821 Dataset [PDF][link], VT1000 Dataset [PDF][link], VT5000 Dataset [PDF][link[9yqv]]

papers

Domain Adaptation

1. Multi-Spectral Salient Object Detection by Adversarial Domain Adaptation, AAAI 2020, Shaoyue Song et al.[PDF]
2. Deep Domain Adaptation Based Multi-spectral Salient Object Detection, TMM 2020, Shaoyue Song et al.[PDF]

Fusion Architecture

1. Multi-Interactive Dual-Decoder for RGB-Thermal Salient Object Detection, TIP 2021, Wu, Zhengtao et al.[PDF]

RGB-T Fusion Tracking

Datasets

GTOT [PDF][link], RGBT234 Dataset [PDF][link], LasHeR Dataset [PDF][link]

papers

1. MTNet: Learning Modality-aware Representation with Transformer for RGBT Tracking, ICME 2023, Ruichao Hou et al. [PDF]
2. Visual Prompt Multi-Modal Tracking, CVPR 2023, Jiawen Zhu et al. [PDF][Code]
3. Efficient RGB-T Tracking via Cross-Modality Distillation, CVPR 2023, Zhang, Tianlu et al. [PDF]
4. Bridging Search Region Interaction with Template for RGB-T Tracking, Hui, CVPR2023, Tianrui et al.[PDF][Code]
5. Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking, TIP2021, Zhang, Pengyu et al. [PDF] TIP 2022, Tu, Zhengzheng et al., [PDF]
6. RGBT tracking via reliable feature configuration, SCIS 2022, Tu, Zhengzheng et al. [PDF]
7. Attribute-Based Progressive Fusion Network for RGBT Tracking, AAAI 2022, Xiao Yun et al. [PDF][Code]
8. Dense Feature Aggregation and Pruning for RGBT Tracking, ACM Multimedia 2022, Yabin Zhu et al. [PDF]
9. Prompting for Multi-Modal Tracking, ACM Multimedia 2022, Jinyu Yang et al. [PDF]
10. Learning Adaptive Attribute-Driven Representation for Real-Time RGB-T Tracking, IJCV 2021, Zhang, Pengyu et al. [PDF]
11. Quality-Aware Feature Aggregation Network for Robust RGBT Tracking, TIV 2021, Zhu, Yabin, [PDF]
12. Challenge-Aware RGBT Tracking, ECCV 2020, Li Chenglong et al. [PDF]
13. Object fusion tracking based on visible and infrared images: A comprehensive review, Information Fusion 2020, Zhang, Xingchen et al., [PDF]
14. RGB-T object tracking: Benchmark and baseline, Pattern Recognition 2019, Li, Chenglong et al., [PDF]
15. Cross-Modal Pattern-Propagation for RGB-T Tracking, CVPR2020, Chaoqun Wang et al., [PDF]