Consistent Multi-and Single-View HDR-Image Reconstruction from Single Exposures - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Consistent Multi-and Single-View HDR-Image Reconstruction from Single Exposures

Abstract

Recently, there have been attempts to obtain high-dynamic range (HDR) images from single exposures and efforts to reconstruct multi-view HDR images using multiple input exposures. However, there have not been any attempts to reconstruct multi-view HDR images from multi-view Single Exposures to the best of our knowledge. We present a two-step methodology to obtain color consistent multi-view HDR reconstructions from single-exposure multi-view low-dynamic-range (LDR) Images. We define a new combination of the Mean Absolute Error and Multi-Scale Structural Similarity Index loss functions to train a network to reconstruct an HDR image from an LDR one. Once trained we use this network to multi-view input. When tested on single images, the outputs achieve competitive results with the state-of-the-art. Quantitative and qualitative metrics applied to our results and to the state-of-the-art show that our HDR expansion is better than others while maintaining similar qualitative reconstruction results. We also demonstrate that applying this network on multi-view images ensures coherence throughout the generated grid of HDR images.
Fichier principal
Vignette du fichier
037-044.pdf (478.92 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-03664202 , version 1 (10-05-2022)

Identifiers

Cite

A Mohan, Jing Zhang, Rémi Cozot, C Loscos. Consistent Multi-and Single-View HDR-Image Reconstruction from Single Exposures. WICED: Eurographics Workshop on Intelligent Cinematography and Editing, Apr 2022, Reims, France. ⟨10.2312/wiced.20221050⟩. ⟨hal-03664202⟩
93 View
176 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More