4 papers · 1 filter
A Subjective Study on a New Sharpness Informed Class of Metrics
Uditangshu Aurangabadkar, Vibhoothi Vibhoothi, Darren Ramsook +1
Perceptual loss functions in Deep Neural Network (DNN) deblurring architectures improve the overall quality of restored images. However, few focus on explicitly targeting sharpness…
A Sharpness Based Loss Function for Removing Out-of-Focus Blur
Uditangshu Aurangabadkar, Darren Ramsook, Anil Kokaram
The success of modern Deep Neural Network (DNN) approaches can be attributed to the use of complex optimization criteria beyond standard losses such as mean absolute error (MAE) or…
A Neural Enhancement Post-Processor with a Dynamic AV1 Encoder Configuration Strategy for CLIC 2024
Darren Ramsook, Anil Kokaram
At practical streaming bitrates, traditional video compression pipelines frequently lead to visible artifacts that degrade perceptual quality. This submission couples the effective…
Learnt Deep Hyperparameter selection in Adversarial Training for compressed video enhancement with perceptual critic
Darren Ramsook, Anil Kokaram
Image based Deep Feature Quality Metrics (DFQMs) have been shown to better correlate with subjective perceptual scores over traditional metrics. The fundamental focus of these DFQM…