CPC H04N 23/741 (2023.01) [G06N 3/08 (2013.01); G06T 5/40 (2013.01); G06T 5/92 (2024.01)] | 20 Claims |
1. A method for generating an HDR image from an input image Iin comprising the steps of:
progressively inferring texture and structural features with learned confidence maps from two exposure gated detail recovering branches (EGDRBs), wherein one of the EGDRBs is adapted to process an image Io induced from the input image with an over-exposure level deviated from the optimal exposure level, and another EGDRB is adapted to process an image Iu induced from the input image Iin with under-exposure level deviated from the optimal exposure level;
processing the input image Iin with a dynamic range expansion branch (DREB) that interacts with EGDRBs for expanding a global dynamic range of the input image Iin with optimal exposure level; and
adaptively merging texture and structural features from the EGDRBs and features from DREB in a feature fusion module (FFM) to generate the HDR image.
|