Computational Photography Methods and Applications

Abstract

persistent challenge in the design and manufacture of digital cameras is how to improve the signal-to-noise performance of these devices while simultaneously maintaining high color fidelity captures. The present industry standard three-color channel system is constrained in that the fewest possible color channels are employed for the purposes of both luminance and chrominance image information detection. Without additional degrees of freedom, for instance, additional color channels, digital camera designs are generally limited to solutions based on improving sensor hardware (larger pixels, lower readout noise, etc.) or better image processing (improved denoising, system-wide image processing chain optimization, etc.) Due to being constrained to three channels, the requirements for improved signal-to-noise and high color fidelity are frequently in opposition to each other, thereby providing a limiting constraint on how much either can be improved. For example, to improve the light sensitivity of the sensor system, one might wish to make the color channels broader spectrally. While this results in lower image noise in the raw capture, the color correction required to restore the color fidelity amplifies the noise so much that there can be a net loss in overall signal-to-noise performance.