DIBR synthesized image quality assessment based on morphological wavelets
Résumé
Most of the Depth Image Based Rendering (DIBR) techniques produce synthesized images which contain nonuniform geometric distortions affecting edges coherency. This type of distortions are challenging for common image quality metrics. Morphological filters maintain important geometric information such as edges across different resolution levels. In this paper, morphological wavelet peak signal-to-noise ratio measure, MW-PSNR, based on morphological wavelet decomposition is proposed to tackle the evaluation of DIBR synthesized images. It is shown that MW-PSNR achieves much higher correlation with human judgment compared to the state-of-the-art image quality measures in this context.
Mots clés
- lifting scheme
- depth image based rendering
- DIBR synthesized image evaluation
- DIBR synthesized image quality assessment
- distortion
- edge coherency
- edge detection
- image filtering
- image quality
- image quality metrics
- Lattices
- morphological wavelet decomposition
- measurement
- morphological filters
- wavelet transforms
- Signal resolution
- rendering (computer graphics)
- quincunx sampling
- nonuniform geometric distortions
- nonseparable morphological wavelet decomposition
- MW-PSNR
- Multi-scale PSNR
- morphological wavelets
- morphological wavelet peak signal-to-noise ratio measure