Publications by authors named "Sadbhawna"
Quality assessment of 3D-synthesized images has traditionally been based on detecting specific categories of distortions such as stretching, black-holes, blurring, etc. However, such approaches have limitations in accurately detecting distortions entirely in 3D synthesized images affecting their performance. This work proposes an algorithm to efficiently detect the distortions and subsequently evaluate the perceptual quality of 3D synthesized images.
View Article and Find Full Text PDFStretching Artifacts Identification for Quality Assessment of 3D-Synthesized Views.
IEEE Trans Image Process
February 2022
Article Synopsis
- Existing Quality Assessment (QA) algorithms struggle to identify stretching artifacts in 3D-synthesized views, as they are outdated and mainly focused on "black-holes," which are now less relevant due to advanced rendering techniques.
- The researchers discovered a link between the amount of stretching artifacts and the overall perceptual quality of the images, leading to the development of a CNN-based algorithm to detect these artifacts.
- To improve the algorithm's effectiveness, they augmented the training dataset by gathering images from related sources, resulting in better performance in assessing 3D-synthesized views compared to current algorithms.