Cross-Modal Transformers for Infrared and Visible Image Fusion
The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Image fusion techniques aim to generate more informative images by merging multiple images of different modalities with complementary information. Despite significant fusion performance improvements of recent learning-based approaches, most fusion algorithms have been developed based on convolutional neural networks (CNNs), which stack deep layers to obtain a large receptive field for feature extraction. However, important details and contexts of the source images may be lost through a series of convolution layers. In this work, we propose a cross-modal transformer-based fusion (CMTFusion) algorithm for infrared and visible image fusion that captures global interactions by faithfully extracting complementary information from source images. Specifically, we first extract the multiscale feature maps of infrared and visible images. Then, we develop cross-modal transformers (CMTs) to retain complementary information in the source images by removing redundancies in both the spatial and channel domains. To this end, we design a gated bottleneck that integrates cross-domain interaction to consider the characteristics of the source images. Finally, a fusion result is obtained by exploiting spatial-channel information in refined feature maps using a fusion block. Experimental results on multiple datasets demonstrate that the proposed algorithm provides better fusion performance than state-of-the-art infrared and visible image fusion algorithms, both quantitatively and qualitatively. Furthermore, we show that the proposed algorithm can be used to improve the performance of computer vision tasks, e.g., object detection and monocular depth estimation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
YOLOv4: Optimal Speed and Accuracy of Object Detection
Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020) · arXiv · doi:10.48550/arxiv.2004.10934 · Cited by 10,307
Making a “Completely Blind” Image Quality Analyzer
Mittal, A., Soundararajan, R., & Bovik, A. C. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2227726 · Cited by 6,766 · cited 1×
“…for discrete cosine features (FMI dct ) [71] and wavelet features (FMI w ) [71], multiscale structural similarity (MS-SSIM) [72], sum of the correlations of differences (SCD) [73], blind/referenceless image spatial quality evaluator (BRISQUE) [74], and natural image quality evaluator (NIQE) [75].”
BackgroundA Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
Scharstein, D., & Szeliski, R. (2002) · International Journal of Computer Vision · doi:10.1023/a:1014573219977 · Cited by 6,740 · cited 1×
“Therefore, we adopt a ranking-based assessment [76] for the overall performance evaluation.”
MethodNo-Reference Image Quality Assessment in the Spatial Domain
Mittal, A., Moorthy, A. K., & Bovik, A. C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2214050 · Cited by 6,064 · cited 1×
“…for discrete cosine features (FMI dct ) [71] and wavelet features (FMI w ) [71], multiscale structural similarity (MS-SSIM) [72], sum of the correlations of differences (SCD) [73], blind/referenceless image spatial quality evaluator (BRISQUE) [74], and natural image quality evaluator (NIQE) [75].”
BackgroundVision Transformers for Dense Prediction
Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01196 · Cited by 2,373
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Tancik, M., Srinivasan, P. P., Mildenhall, B., Fridovich-Keil, S., Raghavan, N., Singhal, U., Ramamoorthi, R., Barron, J. T., & Ng, R. (2020) · arXiv · doi:10.48550/arxiv.2006.10739 · Cited by 1,459 · cited 1×
“Learning-based algorithms tend to lose the high-frequency information in the source images due to the bias of the CNNs, leading to a loss of fine detail and to visible artifacts in the final results [68].”
BackgroundLiu, J., Fan, X., Huang, Z., Wu, G., Liu, R., Zhong, W., & Luo, Z. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00571 · Cited by 1,336 · cited 7×
“…deep learning-based fusion algorithms [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41] only capture the local information in the source images in a fixed-size window; thus they have limited ability to capture global…”
BackgroundMethodInfluentialMultispectral pedestrian detection: Benchmark dataset and baseline
Hwang, S., Park, J., Kim, N., Choi, Y., & Kweon, I. S. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298706 · Cited by 1,249 · cited 2×
“We train the proposed CMT-Fusion algorithm using only the KAIST dataset [63], which contains 95,000 pairs of well-aligned visible and infrared images.”
MethodCMX: Cross-Modal Fusion for RGB-X Semantic Segmentation With Transformers
Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., & Stiefelhagen, R. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3300537 · Cited by 731 · cited 3×
“Furthermore, global interactions are captured with self-attention only in the spatial domain in [55], although the feature maps contain different information in different domains.”
BackgroundAttention Bottlenecks for Multimodal Fusion
Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., & Sun, C. (2021) · arXiv · doi:10.48550/arxiv.2107.00135 · Cited by 400
Metadata
- Authors
- Park, S., Vien, A. G., & Lee, C.
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2024-02
- Volume
- 34
- Issue
- 2
- Pages
- 770-785
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W4382119107
- Cited by
- 206
- References
- 12
- FWCI
- 22.75
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.