Inference-time Trajectory Optimization for Manga Image Editing
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914431310495744 |
|---|---|
| author | Furuta, Ryosuke |
| author_facet | Furuta, Ryosuke |
| contents | We present an inference-time adaptation method that tailors a pretrained image editing model to each input manga image using only the input image itself. Despite recent progress in pretrained image editing, such models often underperform on manga because they are trained predominantly on natural-image data. Re-training or fine-tuning large-scale models on manga is, however, generally impractical due to both computational cost and copyright constraints. To address this issue, our method slightly corrects the generation trajectory at inference time so that the input image can be reconstructed more faithfully under an empty prompt. Experimental results show that our method consistently outperforms existing baselines while incurring only negligible computational overhead. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27790 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Inference-time Trajectory Optimization for Manga Image Editing Furuta, Ryosuke Computer Vision and Pattern Recognition We present an inference-time adaptation method that tailors a pretrained image editing model to each input manga image using only the input image itself. Despite recent progress in pretrained image editing, such models often underperform on manga because they are trained predominantly on natural-image data. Re-training or fine-tuning large-scale models on manga is, however, generally impractical due to both computational cost and copyright constraints. To address this issue, our method slightly corrects the generation trajectory at inference time so that the input image can be reconstructed more faithfully under an empty prompt. Experimental results show that our method consistently outperforms existing baselines while incurring only negligible computational overhead. |
| title | Inference-time Trajectory Optimization for Manga Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.27790 |