Perceptual Learned Image Compression via End-to-End JND-Based Optimization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909093392809984 |
|---|---|
| author | Pakdaman, Farhad Nami, Sanaz Gabbouj, Moncef |
| author_facet | Pakdaman, Farhad Nami, Sanaz Gabbouj, Moncef |
| contents | Emerging Learned image Compression (LC) achieves significant improvements in coding efficiency by end-to-end training of neural networks for compression. An important benefit of this approach over traditional codecs is that any optimization criteria can be directly applied to the encoder-decoder networks during training. Perceptual optimization of LC to comply with the Human Visual System (HVS) is among such criteria, which has not been fully explored yet. This paper addresses this gap by proposing a novel framework to integrate Just Noticeable Distortion (JND) principles into LC. Leveraging existing JND datasets, three perceptual optimization methods are proposed to integrate JND into the LC training process: (1) Pixel-Wise JND Loss (PWL) prioritizes pixel-by-pixel fidelity in reproducing JND characteristics, (2) Image-Wise JND Loss (IWL) emphasizes on overall imperceptible degradation levels, and (3) Feature-Wise JND Loss (FWL) aligns the reconstructed image features with perceptually significant features. Experimental evaluations demonstrate the effectiveness of JND integration, highlighting improvements in rate-distortion performance and visual quality, compared to baseline methods. The proposed methods add no extra complexity after training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02836 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Perceptual Learned Image Compression via End-to-End JND-Based Optimization Pakdaman, Farhad Nami, Sanaz Gabbouj, Moncef Image and Video Processing Computer Vision and Pattern Recognition Multimedia Emerging Learned image Compression (LC) achieves significant improvements in coding efficiency by end-to-end training of neural networks for compression. An important benefit of this approach over traditional codecs is that any optimization criteria can be directly applied to the encoder-decoder networks during training. Perceptual optimization of LC to comply with the Human Visual System (HVS) is among such criteria, which has not been fully explored yet. This paper addresses this gap by proposing a novel framework to integrate Just Noticeable Distortion (JND) principles into LC. Leveraging existing JND datasets, three perceptual optimization methods are proposed to integrate JND into the LC training process: (1) Pixel-Wise JND Loss (PWL) prioritizes pixel-by-pixel fidelity in reproducing JND characteristics, (2) Image-Wise JND Loss (IWL) emphasizes on overall imperceptible degradation levels, and (3) Feature-Wise JND Loss (FWL) aligns the reconstructed image features with perceptually significant features. Experimental evaluations demonstrate the effectiveness of JND integration, highlighting improvements in rate-distortion performance and visual quality, compared to baseline methods. The proposed methods add no extra complexity after training. |
| title | Perceptual Learned Image Compression via End-to-End JND-Based Optimization |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2402.02836 |