Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration

Authors: Huangxing Lin, Yuhang Dong, Xinghao Ding, Tianpeng Liu, Yongxiang Liu

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show that the proposed method significantly outperforms existing unsupervised pan-sharpening methods.
Researcher Affiliation Academia Huangxing Lin1, Yuhang Dong2, Xinghao Ding2, Tianpeng Liu1*, Yongxiang Liu1 1College of Electronic Science, National University of Defense Technology, China 2School of Informatics, Xiamen University, China
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to its own source code for the methodology described.
Open Datasets Yes We utilize three satellite datasets, namely Gao Fen2 (GF2), Quick Bird (QB), and World View-3 (WV3), to assess the effectiveness of the proposed method.
Dataset Splits No The paper describes how reduced-resolution data is synthesized for evaluation and how full-resolution data is used for both training and testing, but it does not provide specific train/validation/test dataset splits with percentages, sample counts, or explicit standard split references for its own model training.
Hardware Specification Yes All experiments are performed on a single NVIDIA Ge Force GTX 3090 GPU.
Software Dependencies No The paper mentions using the 'Pytorch framework and the Adam optimizer' but does not specify their version numbers or other software dependencies with versions.
Experiment Setup Yes During the initial half of the training process, the learning rate is fixed at 0.0002, and in the latter half of the training, the learning rate linearly decays to 0. [...] To mitigate the adverse effects of Lgrad, we set β to 1 and λ to 3.