Publications by authors named "Dragan D Kukolj"
Images synthesized using depth-image-based-rendering (DIBR) techniques may suffer from complex structural distortions. The goal of the primary visual cortex and other parts of brain is to reduce redundancies of input visual signal in order to discover the intrinsic image structure, and thus create sparse image representation. Human visual system (HVS) treats images on several scales and several levels of resolution when perceiving the visual scene.
View Article and Find Full Text PDFFast Blind Quality Assessment of DIBR-Synthesized Video Based on High-High Wavelet Subband.
IEEE Trans Image Process
November 2019
Article Synopsis
- Free-viewpoint video uses depth-image-based rendering (DIBR) to create video sequences from limited viewpoints, requiring reliable quality metrics for evaluation.
- Existing no-reference quality metrics effectively assess synthesized images but struggle with video due to added temporal flickering.
- A new fast no-reference quality metric called No-Reference Morphological Wavelet with Threshold (NR_MWT) is introduced, which efficiently evaluates synthesized video quality by focusing on high-frequency content and achieving better performance than existing metrics without using machine learning.