Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915593797500928 |
|---|---|
| author | Qiao, Xin Poggi, Matteo Wei, Xing Deng, Pengchao Zhou, Yanhui Mattoccia, Stefano |
| author_facet | Qiao, Xin Poggi, Matteo Wei, Xing Deng, Pengchao Zhou, Yanhui Mattoccia, Stefano |
| contents | Under-display ToF imaging aims to achieve accurate depth sensing through a ToF camera placed beneath a screen panel. However, transparent OLED (TOLED) layers introduce severe degradations-such as signal attenuation, multi-path interference (MPI), and temporal noise-that significantly compromise depth quality. To alleviate this drawback, we propose Learnable Fractional Reaction-Diffusion Dynamics (LFRD2), a hybrid framework that combines the expressive power of neural networks with the interpretability of physical modeling. Specifically, we implement a time-fractional reaction-diffusion module that enables iterative depth refinement with dynamically generated differential orders, capturing long-term dependencies. In addition, we introduce an efficient continuous convolution operator via coefficient prediction and repeated differentiation to further improve restoration quality. Experiments on four benchmark datasets demonstrate the effectiveness of our approach. The code is publicly available at https://github.com/wudiqx106/LFRD2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01704 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond Qiao, Xin Poggi, Matteo Wei, Xing Deng, Pengchao Zhou, Yanhui Mattoccia, Stefano Computer Vision and Pattern Recognition Under-display ToF imaging aims to achieve accurate depth sensing through a ToF camera placed beneath a screen panel. However, transparent OLED (TOLED) layers introduce severe degradations-such as signal attenuation, multi-path interference (MPI), and temporal noise-that significantly compromise depth quality. To alleviate this drawback, we propose Learnable Fractional Reaction-Diffusion Dynamics (LFRD2), a hybrid framework that combines the expressive power of neural networks with the interpretability of physical modeling. Specifically, we implement a time-fractional reaction-diffusion module that enables iterative depth refinement with dynamically generated differential orders, capturing long-term dependencies. In addition, we introduce an efficient continuous convolution operator via coefficient prediction and repeated differentiation to further improve restoration quality. Experiments on four benchmark datasets demonstrate the effectiveness of our approach. The code is publicly available at https://github.com/wudiqx106/LFRD2. |
| title | Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.01704 |