J Otsuka, M Yoshimura, T Ohashi - arXiv preprint arXiv:2303.13916, 2023 - arxiv.org
Unprocessed sensor outputs (RAW images) potentially improve both low-level and high- level computer vision algorithms, but the lack of large-scale RAW image datasets is a barrier …
A Liu, S Mu, S Xu - arXiv preprint arXiv:2409.02497, 2024 - arxiv.org
Autonomous driving algorithms usually employ sRGB images as model input due to their compatibility with the human visual system. However, visually pleasing sRGB images are …