Image demosaicking and denoising are the two key fundamental steps in digital camera pipelines, aiming to reconstruct clean color images from noisy luminance readings. In this paper, we propose and study Wild-JDD, a novel learning framework for joint demosaicking and denoising in the wild. In contrast to previous works which generally assume the ground truth of training data is a perfect reflection of the reality, we consider here the more common imperfect case of ground truth uncertainty in the wild. We first illustrate its manifestation as various kinds of artifacts including zipper effect, color moire and residual noise. Then we formulate a two-stage data degradation process to capture such ground truth uncertainty, where a conjugate prior distribution is imposed upon a base distribution. After that, we derive an evidence lower bound (ELBO) loss to train a neural network that approximates the parameters of the conjugate prior distribution conditioned on the degraded input. Finally, to further enhance the performance for out-of-distribution input, we design a simple but effective fine-tuning strategy by taking the input as a weakly informative prior. Taking into account ground truth uncertainty, Wild-JDD enjoys good interpretability during optimization. Extensive experiments validate that it outperforms state-of-the-art schemes on joint demosaicking and denoising tasks on both synthetic and realistic raw datasets.
Joint Demosaicking and Denoising Benefits from a Two-stage Training Strategy
Inner Mongolia University（内蒙古大学）；CNRS（法国国家科学研究中心）；ENS Paris-Saclay（巴黎-萨克雷高等师范学校）；Université Paris-Saclay（巴黎-萨克雷大学）；The Chinese University of Hong Kong（香港中文大学）
Combining Pre- and Post-Demosaicking Noise Removal for RAW Video
Institute of Applied Computing and Community Code (IAC3)（应用计算与社区代码研究所（IAC3））；Universitat de les Illes Balears（巴利阿里群岛大学）；Huawei Technologies France（华为法国技术公司）
OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision
Harbin Institute of Technology（哈尔滨工业大学）；Shenzhen University（深圳大学）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology, Chongqing Research Institute（哈尔滨工业大学重庆研究院）；CECloud Computing Technology Co., Ltd（天翼云计算技术有限公司）
