Mohan, AdityaZhang, JingCozot, RémiLoscos, CelineSauvage, BasileHasic-Telalovic, Jasminka2022-04-222022-04-222022978-3-03868-171-71017-4656https://doi.org/10.2312/egp.20221004https://diglib.eg.org:443/handle/10.2312/egp20221004We propose a CNN-based approach for reconstructing HDR images from just a single exposure. It predicts the saturated areas of LDR images and then blends the linearized input with the predicted outputs. Two loss functions are used: the Mean Absolute Error and the Multi-Scale Structural Similarity Index. The choice of these loss functions allows us to outperform previous algorithms in the reconstructed dynamic range. Once the network trained, we input multi-view images to it to output multi-view coherent images.Attribution 4.0 International License10.2312/egp.2022100411-122 pages