1 code implementation • CVPR 2023 • Zehua Sheng, Zhu Yu, Xiongwei Liu, Si-Yuan Cao, Yuqi Liu, Hui-Liang Shen, Huaqi Zhang
Instead of aligning the input images via conventional stereo matching, we aggregate structures from the guidance image to estimate a clean structure map for the noisy target image, which is then used to regress the final denoising result with a spatially variant linear representation model.