### Environment Setup using Conda Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README.md This snippet sets up the environment for the DCEvo project using Conda. It creates a virtual environment named DCEvo with Python 3.9 and installs the required packages from the requirements.txt file. ```Shell conda create -n DCEvo python=3.9 conda activate DCEvo pip install -r requirements.txt ``` -------------------------------- ### Environment Setup using Conda Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README_zh.md This snippet creates a virtual environment named DCEvo with Python 3.9 and installs the required packages from the requirements.txt file. It ensures the project dependencies are properly managed and isolated. ```Shell # create virtual environment conda create -n DCEvo python=3.9 conda activate DCEvo # install requirements pip install -r requirements.txt ``` -------------------------------- ### Data Annotation Example Source: https://github.com/beate-suy-zhang/dcevo/blob/main/datasets/M3FD/train/labels/00405.txt This snippet shows the format of object detection annotations. Each line represents an object instance with class label, bounding box coordinates, and dimensions. ```plaintext 0 0.0263671875 0.6705729166666666 0.05078125 0.28125 0 0.09521484375 0.6595052083333333 0.0751953125 0.3059895833333333 0 0.06201171875 0.626953125 0.0068359375 0.022135416666666664 0 0.19873046875 0.6341145833333333 0.0283203125 0.140625 0 0.2236328125 0.6360677083333333 0.025390625 0.13671875 0 0.25390625 0.6399739583333333 0.0234375 0.11328125 0 0.27880859375 0.6354166666666666 0.0263671875 0.11979166666666666 0 0.36181640625 0.6569010416666666 0.0107421875 0.06640625 0 0.37060546875 0.6536458333333333 0.0107421875 0.06770833333333333 0 0.380859375 0.6595052083333333 0.01171875 0.05598958333333333 0 0.39453125 0.66015625 0.015625 0.057291666666666664 1 0.51025390625 0.6953125 0.2060546875 0.21354166666666666 1 0.6484375 0.650390625 0.140625 0.12109375 1 0.74365234375 0.61328125 0.1181640625 0.12239583333333333 1 0.88427734375 0.6158854166666666 0.1728515625 0.171875 ``` -------------------------------- ### Test Pure Image Fusion Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README.md This snippet demonstrates how to test the pure fusion method using the test_Fusion.py script. It assumes that the checkpoints are located in the DCEvo/ckpt directory. ```Python python test_Fusion.py ``` -------------------------------- ### Testing Task-Guided Image Fusion with Python Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README_zh.md This snippet executes the test_task_guided_fusion.py script to test task-guided image fusion. It requires RGB pure fusion images to be generated in the "DCEvo/datasets/M3FD/images" directory beforehand. ```Python python test_task_guided_fusion.py ``` -------------------------------- ### Testing Image Fusion with Python Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README_zh.md This snippet executes the test_Fusion.py script to perform image fusion using pre-trained model parameters. The model parameters are assumed to be located in the "DCEvo/ckpt" directory. ```Python python test_Fusion.py ``` -------------------------------- ### Test Task-Guided Image Fusion Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README.md This snippet demonstrates how to test the task-guided fusion method using the test_task_guided_fusion.py script. It requires that RGB Pure Fusion images are generated in the DCEvo/datasets/M3FD/images directory. ```Python python test_task_guided_fusion.py ``` -------------------------------- ### Training Task-Guided Image Fusion with Python Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README_zh.md This snippet executes the DCEvo_train.py script to train the task-guided image fusion model. It requires RGB pure fusion images to be generated in the "DCEvo/datasets/M3FD/images" directory before training. ```Python python DCEvo_train.py ``` -------------------------------- ### Train Task-Guided Image Fusion Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README.md This snippet shows how to train the task-guided fusion method using the DCEvo_train.py script. It requires that RGB Pure Fusion images are generated in the DCEvo/datasets/M3FD/train/images directory. ```Python python DCEvo_train.py ``` -------------------------------- ### Colorizing Grayscale Images with Python Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README_zh.md This snippet runs the tocolor.py script to colorize grayscale images. This is used for task-guided image fusion training and testing. The script likely takes grayscale images as input and produces colorized images as output. ```Python python tocolor.py ``` -------------------------------- ### BibTeX entry for citing DCEvo Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README_zh.md This BibTeX entry provides the citation information for the DCEvo paper. It includes the title, authors, journal, and year of publication, which is useful for academic referencing. ```BibTeX @article{li2025difiisr, title={DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion}, author={Liu, Jinyuan and Zhang, Bowei and Mei, Qingyun and Li, Xingyuan and Zou, Yang and Jiang, Zhiying and Ma, Long and Liu, Risheng and Fan, Xin}, journal={arXiv preprint arXiv:2503.17673}, year={2025} } ``` -------------------------------- ### Color Gray Images Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README.md This snippet shows how to color the output gray images using the tocolor.py script. This is useful for task-guided image fusion training and testing. ```Python python tocolor.py ``` -------------------------------- ### Citation Information Source: https://github.com/beate-suy-zhang/dcevo/blob/main/README.md This snippet provides the citation information for the DCEvo project. It includes the title, authors, journal, and year of publication. ```BibTeX @article{li2025difiisr, title={DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion}, author={Liu, Jinyuan and Zhang, Bowei and Mei, Qingyun and Li, Xingyuan and Zou, Yang and Jiang, Zhiying and Ma, Long and Liu, Risheng and Fan, Xin}, journal={arXiv preprint arXiv:2503.17673}, year={2025} } ``` -------------------------------- ### Object Detection Data Format Source: https://github.com/beate-suy-zhang/dcevo/blob/main/datasets/M3FD/train/labels/02195.txt Each line represents an object instance. The values are: class label, normalized x-coordinate of the bounding box center, normalized y-coordinate of the bounding box center, normalized width of the bounding box, and normalized height of the bounding box. ```plain text 1 0.01025390625 0.90234375 0.0185546875 0.06770833333333333 1 0.0439453125 0.8958333333333333 0.048828125 0.0546875 1 0.51171875 0.8841145833333333 0.03125 0.028645833333333332 1 0.55224609375 0.88671875 0.0341796875 0.0390625 1 0.57421875 0.8802083333333333 0.017578125 0.03645833333333333 1 0.587890625 0.8815104166666666 0.017578125 0.028645833333333332 1 0.599609375 0.8776041666666666 0.017578125 0.0234375 1 0.60498046875 0.8893229166666666 0.0185546875 0.033854166666666664 1 0.62646484375 0.90625 0.0537109375 0.05208333333333333 1 0.6669921875 0.8932291666666666 0.033203125 0.033854166666666664 2 0.7470703125 0.8776041666666666 0.119140625 0.125 0 0.15771484375 0.9212239583333333 0.0283203125 0.13151041666666666 0 0.92529296875 0.896484375 0.0224609375 0.053385416666666664 1 0.28662109375 0.8893229166666666 0.0341796875 0.03125 1 0.33154296875 0.8860677083333333 0.0361328125 0.024739583333333332 1 0.14697265625 0.88671875 0.0380859375 0.03645833333333333 1 0.2333984375 0.884765625 0.056640625 0.045572916666666664 3 0.56640625 0.728515625 0.015625 0.04817708333333333 3 0.63916015625 0.732421875 0.0166015625 0.04817708333333333 2 0.32275390625 0.8723958333333333 0.0439453125 0.041666666666666664 0 0.18212890625 0.9231770833333333 0.0224609375 0.11979166666666666 1 0.0830078125 0.9010416666666666 0.07421875 0.06770833333333333 ``` -------------------------------- ### Object Detection Data Format Source: https://github.com/beate-suy-zhang/dcevo/blob/main/datasets/M3FD/train/labels/00118.txt Each line represents an object instance with the format: class_label x_center y_center width height. The coordinates are likely normalized to the range [0, 1]. ```plain text 1 0.23681640625 0.6197916666666666 0.2998046875 0.36197916666666663 1 0.0537109375 0.5703125 0.10546875 0.09375 0 0.35986328125 0.5299479166666666 0.0146484375 0.0625 0 0.3779296875 0.5325520833333333 0.017578125 0.0625 0 0.4814453125 0.5358072916666666 0.01171875 0.045572916666666664 0 0.5029296875 0.5377604166666666 0.015625 0.05208333333333333 0 0.5390625 0.5364583333333333 0.017578125 0.057291666666666664 0 0.60205078125 0.5169270833333333 0.0107421875 0.015625 1 0.59814453125 0.548828125 0.0498046875 0.045572916666666664 1 0.671875 0.5358072916666666 0.03515625 0.04296875 1 0.7109375 0.53515625 0.046875 0.046875 3 0.90673828125 0.392578125 0.0224609375 0.06380208333333333 0 0.79931640625 0.533203125 0.0205078125 0.06380208333333333 0 0.8076171875 0.53125 0.015625 0.06510416666666666 3 0.515625 0.39322916666666663 0.017578125 0.057291666666666664 3 0.17236328125 0.40299479166666663 0.0263671875 0.06380208333333333 3 0.01611328125 0.3665364583333333 0.0283203125 0.08203125 ``` === COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.