29 citations · 88 across the 22 of their papers we have counts for
26 papers
A Reference-Free Framework for Evaluating Single-Frame ISP Pipelines
Yujin Cho, Sira Ferradans, Jean-Michel Morel +2
Evaluating camera image signal processing (ISP) pipelines requires measuring low-level artifacts introduced by operations such as denoising, demosaicing, tone mapping, and compress…
Adapting MIMO video restoration networks to low latency constraints
Valéry Dewil, Zhe Zheng, Arnaud Barral +7
MIMO (multiple input, multiple output) approaches are a recent trend in neural network architectures for video restoration problems, where each network evaluation produces multiple…
How to Best Combine Demosaicing and Denoising?
Yu Guo, Qiyu Jin, Jean-Michel Morel +1
Image demosaicing and denoising play a critical role in the raw imaging pipeline. These processes have often been treated as independent, without considering their interactions. In…
Fast, nonlocal and neural: a lightweight high quality solution to image denoising
Yu Guo, Axel Davy, Gabriele Facciolo +2
With the widespread application of convolutional neural networks (CNNs), the traditional model based denoising algorithms are now outperformed. However, CNNs face two problems. Fir…
IAdet: Simplest human-in-the-loop object detection
Franco Marchesoni-Acland, Gabriele Facciolo
This work proposes a strategy for training models while annotating data named Intelligent Annotation (IA). IA involves three modules: (1) assisted data annotation, (2) background m…
Optimal and Efficient Binary Questioning for Human-in-the-Loop Annotation
Franco Marchesoni-Acland, Jean-Michel Morel, Josselin Kherroubi +1
Even though data annotation is extremely important for interpretability, research and development of artificial intelligence solutions, most research efforts such as active learnin…