Computational imaging pipelines (CIPs) convert the raw output of imaging sensors into the high-quality images that are used for further processing. This work studies how Block-Matching and 3D filtering (BM3D), a state-of-the-art denoising algorithm can be implemented to meet the demands of user-interactive (UI) applications. Denoising is the most computationally demanding stage of a CIP taking more than 95% of time on a highly-optimized software implementation [29]. We analyze the performance and energy consumption of optimized software implementations on three commodity platforms and find that their performance is inadequate.

Stereotypes about women's place among creators of technology still exist. As a result, women engineers and computer scientists must find ways to manage the conflict between their identities as women and as creators of technology. Many women manage the conflict by hiding or denying their feminine identity. We found that this strategy becomes particularly evident when discussing experiences of sexism. Focus groups with women graduate students identified many instances of sexism, but found that women tended to deny or ignore the sexism. Because sexism communicates the view that women do not fit in the culture of computing, it increases the difficulty of combining a feminine gender identity with a technical identity. Many women try to meet this challenge by minimizing their femininity, or acting like one of the guys. These coping strategies may be effective for enabling individual persistence, but they permit persistence of an inhospitable environment. Adopting practices known to reduce the incidence of sexism and mitigate its negative impact could help retain women graduate students in computing.