InstaRevive: One-Step Image Enhancement via Dynamic Score Matching
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909588253573120 |
|---|---|
| author | Zhu, Yixuan Wang, Haolin Li, Ao Zhao, Wenliang Tang, Yansong Niu, Jingxuan Chen, Lei Zhou, Jie Lu, Jiwen |
| author_facet | Zhu, Yixuan Wang, Haolin Li, Ao Zhao, Wenliang Tang, Yansong Niu, Jingxuan Chen, Lei Zhou, Jie Lu, Jiwen |
| contents | Image enhancement finds wide-ranging applications in real-world scenarios due to complex environments and the inherent limitations of imaging devices. Recent diffusion-based methods yield promising outcomes but necessitate prolonged and computationally intensive iterative sampling. In response, we propose InstaRevive, a straightforward yet powerful image enhancement framework that employs score-based diffusion distillation to harness potent generative capability and minimize the sampling steps. To fully exploit the potential of the pre-trained diffusion model, we devise a practical and effective diffusion distillation pipeline using dynamic control to address inaccuracies in updating direction during score matching. Our control strategy enables a dynamic diffusing scope, facilitating precise learning of denoising trajectories within the diffusion model and ensuring accurate distribution matching gradients during training. Additionally, to enrich guidance for the generative power, we incorporate textual prompts via image captioning as auxiliary conditions, fostering further exploration of the diffusion model. Extensive experiments substantiate the efficacy of our framework across a diverse array of challenging tasks and datasets, unveiling the compelling efficacy and efficiency of InstaRevive in delivering high-quality and visually appealing results. Code is available at https://github.com/EternalEvan/InstaRevive. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15513 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InstaRevive: One-Step Image Enhancement via Dynamic Score Matching Zhu, Yixuan Wang, Haolin Li, Ao Zhao, Wenliang Tang, Yansong Niu, Jingxuan Chen, Lei Zhou, Jie Lu, Jiwen Computer Vision and Pattern Recognition Image enhancement finds wide-ranging applications in real-world scenarios due to complex environments and the inherent limitations of imaging devices. Recent diffusion-based methods yield promising outcomes but necessitate prolonged and computationally intensive iterative sampling. In response, we propose InstaRevive, a straightforward yet powerful image enhancement framework that employs score-based diffusion distillation to harness potent generative capability and minimize the sampling steps. To fully exploit the potential of the pre-trained diffusion model, we devise a practical and effective diffusion distillation pipeline using dynamic control to address inaccuracies in updating direction during score matching. Our control strategy enables a dynamic diffusing scope, facilitating precise learning of denoising trajectories within the diffusion model and ensuring accurate distribution matching gradients during training. Additionally, to enrich guidance for the generative power, we incorporate textual prompts via image captioning as auxiliary conditions, fostering further exploration of the diffusion model. Extensive experiments substantiate the efficacy of our framework across a diverse array of challenging tasks and datasets, unveiling the compelling efficacy and efficiency of InstaRevive in delivering high-quality and visually appealing results. Code is available at https://github.com/EternalEvan/InstaRevive. |
| title | InstaRevive: One-Step Image Enhancement via Dynamic Score Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15513 |