Reconfigurable Snapshot HDR Imaging Using Coded Masks and Inception Network

High Dynamic Range (HDR) image acquisition from a single image capture, also known as snapshot HDR imaging, is challenging because the bit depths of camera sensors are far from sufficient to cover the full dynamic range of the scene. Existing HDR techniques focus either on algorithmic reconstruction or hardware modification to extend the dynamic range. In this paper we propose a joint design for snapshot HDR imaging by devising a spatially-varying modulation mask in the hardware as well as building an inception network to reconstruct the HDR image. We achieve a reconfigurable HDR camera design that does not require custom sensors, and instead can be reconfigured between HDR and conventional mode with very simple calibration steps. We demonstrate that the proposed hardware-software solution offers a flexible yet robust way to modulating per-pixel exposures, and the network requires little knowledge of the hardware to faithfully reconstruct the HDR image. Comparison results show that our method outperforms state of the art in terms of visual perception quality.

Alghamdi, M., Fu, Q., Thabet, A., & Heidrich, W. (2019). Reconfigurable Snapshot HDR Imaging Using Coded Masks and Inception Network. Vision, Modeling and Visualization.

This work was supported by King Abdullah University of Science and Technology as part of VCC center baseline funding. Masheal Alghamdi is supported by King Abdulaziz City for Science and Technologyscholarship

The Eurographics Association

Conference/Event Name
VMV 2019, 24th International Symposium on Vision, Modeling, and Visualization


Additional Links

Permanent link to this record