Seed Selection for Human-Oriented Image Reconstruction via Guided Diffusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908472490065920 |
|---|---|
| author | Tatsumi, Yui Zeng, Ziyue Watanabe, Hiroshi |
| author_facet | Tatsumi, Yui Zeng, Ziyue Watanabe, Hiroshi |
| contents | Conventional methods for scalable image coding for humans and machines require the transmission of additional information to achieve scalability. A recent diffusion-based approach avoids this by generating human-oriented images from machine-oriented images without extra bitrate. However, it utilizes a single random seed, which may lead to suboptimal image quality. In this paper, we propose a seed selection method that identifies the optimal seed from multiple candidates to improve image quality without increasing the bitrate. To reduce the computational cost, selection is performed based on intermediate outputs obtained from early steps of the reverse diffusion process. Experimental results demonstrate that our proposed method outperforms the baseline, which uses a single random seed without selection, across multiple evaluation metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05363 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Seed Selection for Human-Oriented Image Reconstruction via Guided Diffusion Tatsumi, Yui Zeng, Ziyue Watanabe, Hiroshi Computer Vision and Pattern Recognition Conventional methods for scalable image coding for humans and machines require the transmission of additional information to achieve scalability. A recent diffusion-based approach avoids this by generating human-oriented images from machine-oriented images without extra bitrate. However, it utilizes a single random seed, which may lead to suboptimal image quality. In this paper, we propose a seed selection method that identifies the optimal seed from multiple candidates to improve image quality without increasing the bitrate. To reduce the computational cost, selection is performed based on intermediate outputs obtained from early steps of the reverse diffusion process. Experimental results demonstrate that our proposed method outperforms the baseline, which uses a single random seed without selection, across multiple evaluation metrics. |
| title | Seed Selection for Human-Oriented Image Reconstruction via Guided Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.05363 |