ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learning

no code implementations • 13 Dec 2023 • Haowen Bai, Zixiang Zhao, Jiangshe Zhang, Yichen Wu, Lilun Deng, Yukun Cui, Shuang Xu, Baisong Jiang

To ensure the fusion module maximally preserves the information from the source images, enabling the reconstruction of the source images from the fused image, we adopt a meta-learning strategy to train the loss proposal module using reconstruction loss.

Meta-Learning Multi-Exposure Image Fusion

Seismic Data Interpolation based on Denoising Diffusion Implicit Models with Resampling

no code implementations • 9 Jul 2023 • Xiaoli Wei, Chunxia Zhang, Hongtao Wang, Chengli Tan, Deng Xiong, Baisong Jiang, Jiangshe Zhang, Sang-Woon Kim

The model training is established on the denoising diffusion probabilistic model, where U-Net is equipped with the multi-head self-attention to match the noise in each step.

Denoising Uncertainty Quantification