High Dynamic Range Imaging with Context-aware Transformer. (arXiv:2304.04416v4 [cs.CV] UPDATED)

Avoiding the introduction of ghosts when synthesising LDR images as high
dynamic range (HDR) images is a challenging task. Convolutional neural networks
(CNNs) are effective for HDR ghost removal in general, but are challenging to
deal with the LDR images if there are large movements or
oversaturation/undersaturation. Existing dual-branch methods combining CNN and
Transformer omit part of the information from non-reference images, while the
features extracted by the CNN-based branch are bound to the kernel size with
small receptive field, …

arxiv cnn cnns context convolutional neural networks deal dynamic features general ghost images imaging information introduction kernel movements networks neural networks part recovery reference small the information transformer