HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911397824167936 |
|---|---|
| author | Jiang, Yuxuan Kwan, Ho Man Peng, Tianhao Gao, Ge Zhang, Fan Zhu, Xiaoqing Sole, Joel Bull, David |
| author_facet | Jiang, Yuxuan Kwan, Ho Man Peng, Tianhao Gao, Ge Zhang, Fan Zhu, Xiaoqing Sole, Joel Bull, David |
| contents | Recent advances in implicit neural representations (INRs) have shown significant promise in modeling visual signals for various low-vision tasks including image super-resolution (ISR). INR-based ISR methods typically learn continuous representations, providing flexibility for generating high-resolution images at any desired scale from their low-resolution counterparts. However, existing INR-based ISR methods utilize multi-layer perceptrons for parameterization in the network; this does not take account of the hierarchical structure existing in local sampling points and hence constrains the representation capability. In this paper, we propose a new \textbf{H}ierarchical encoding based \textbf{I}mplicit \textbf{I}mage \textbf{F}unction for continuous image super-resolution, \textbf{HIIF}, which leverages a novel hierarchical positional encoding that enhances the local implicit representation, enabling it to capture fine details at multiple scales. Our approach also embeds a multi-head linear attention mechanism within the implicit attention network by taking additional non-local information into account. Our experiments show that, when integrated with different backbone encoders, HIIF outperforms the state-of-the-art continuous image super-resolution methods by up to 0.17dB in PSNR. The source code of HIIF will be made publicly available at \url{www.github.com}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03748 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution Jiang, Yuxuan Kwan, Ho Man Peng, Tianhao Gao, Ge Zhang, Fan Zhu, Xiaoqing Sole, Joel Bull, David Computer Vision and Pattern Recognition Recent advances in implicit neural representations (INRs) have shown significant promise in modeling visual signals for various low-vision tasks including image super-resolution (ISR). INR-based ISR methods typically learn continuous representations, providing flexibility for generating high-resolution images at any desired scale from their low-resolution counterparts. However, existing INR-based ISR methods utilize multi-layer perceptrons for parameterization in the network; this does not take account of the hierarchical structure existing in local sampling points and hence constrains the representation capability. In this paper, we propose a new \textbf{H}ierarchical encoding based \textbf{I}mplicit \textbf{I}mage \textbf{F}unction for continuous image super-resolution, \textbf{HIIF}, which leverages a novel hierarchical positional encoding that enhances the local implicit representation, enabling it to capture fine details at multiple scales. Our approach also embeds a multi-head linear attention mechanism within the implicit attention network by taking additional non-local information into account. Our experiments show that, when integrated with different backbone encoders, HIIF outperforms the state-of-the-art continuous image super-resolution methods by up to 0.17dB in PSNR. The source code of HIIF will be made publicly available at \url{www.github.com}. |
| title | HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03748 |