Details

Autor(en) / Beteiligte

• Yang, Yingjie
• Wang, Yongfang
• Zhang, Han

Titel

DRBR-HDR: Dual-Branch recursive band reconstruction network for HDR with large motions

Ist Teil von

• Journal of visual communication and image representation, 2023-02, Vol.90, p.103713, Article 103713

Ort / Verlag

Elsevier Inc

Erscheinungsjahr

2023

Link zum Volltext

Quelle

Elsevier ScienceDirect Journals Complete

Beschreibungen/Notizen

• •The global features are extracted to help local features from different receptive fields for efficient feature alignment.•The interactive attention mechanism is introduced to local branch to alleviate ghosting artifacts.•The band representation network is proposed to better repair missing areas from coarse to fine.•Multiscale loss function is used to help network gradually learn to reconstruction without artifact.•The network is robust and able to produce faithful information in the regions with missing content. Ghosting artifacts due to misaligned imaging and missing content of the moving regions are major challenges of synthesizing high dynamic range (HDR) images from multiple low-dynamic range (LDR) with different exposures in dynamic scenes. Therefore, it hopes the HDR reconstruction model can align the LDRs’ features and restore the missing content without artifacts. In the paper, a new dual-branch recursive band reconstruction network for high dynamic range (DRBR-HDR) is proposed to generate credible result in missing content regions, which not only uses global features as supplementary information to help local features from different receptive fields for efficient feature alignment but also designs a series of coarse-to-fine band representation to better repair missing areas in the process of recursion. In addition, we introduce an interactive attention mechanism for local branches to alleviate ghosting artifacts. The experimental results demonstrate that DRBR-HDR achieves state-of-the-art performance compared with that of the prevailing HDR reconstruction methods in various challenging scenes. Index Terms—inverse tone mapping, band reconstruction, global features, high dynamic range images.