Details

Autor(en) / Beteiligte

• Niu, Yuzhen
• Wu, Jianbin
• Liu, Wenxi
• Guo, Wenzhong
• Lau, Rynson W. H.

Titel

HDR-GAN: HDR Image Reconstruction From Multi-Exposed LDR Images With Large Motions

Ist Teil von

• IEEE transactions on image processing, 2021, Vol.30, p.3885-3896

Ort / Verlag

United States: IEEE

Erscheinungsjahr

2021

Link zum Volltext

• Volltext

Quelle

IEEE Xplore Digital Library

Beschreibungen/Notizen

• Synthesizing high dynamic range (HDR) images from multiple low-dynamic range (LDR) exposures in dynamic scenes is challenging. There are two major problems caused by the large motions of foreground objects. One is the severe misalignment among the LDR images. The other is the missing content due to the over-/under-saturated regions caused by the moving objects, which may not be easily compensated for by the multiple LDR exposures. Thus, it requires the HDR generation model to be able to properly fuse the LDR images and restore the missing details without introducing artifacts. To address these two problems, we propose in this paper a novel GAN-based model, HDR-GAN , for synthesizing HDR images from multi-exposed LDR images. To our best knowledge, this work is the first GAN-based approach for fusing multi-exposed LDR images for HDR reconstruction. By incorporating adversarial learning, our method is able to produce faithful information in the regions with missing content. In addition, we also propose a novel generator network, with a reference-based residual merging block for aligning large object motions in the feature domain, and a deep HDR supervision scheme for eliminating artifacts of the reconstructed HDR images. Experimental results demonstrate that our model achieves state-of-the-art reconstruction performance over the prior HDR methods on diverse scenes.