Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918437506252800 |
|---|---|
| author | Kim, Bryan Sangwoo Park, Jonghyun Ye, Jong Chul |
| author_facet | Kim, Bryan Sangwoo Park, Jonghyun Ye, Jong Chul |
| contents | Text-conditioned diffusion models have advanced image and video super-resolution by using prompts as semantic priors, and modern super-resolution pipelines typically rely on latent tiling to scale to high resolutions. In practice, a single global caption is used with the latent tiling, often causing prompt misguidance. Specifically, a coarse global prompt often misses localized details (errors of omission) and provides locally irrelevant guidance (errors of commission) which leads to substandard results at the tile level. To solve this, we propose Tiled Prompts, a unified framework for image and video super-resolution that generates a tile-specific prompt for each latent tile and performs super-resolution under locally text-conditioned posteriors to resolve prompt misguidance with minimal overhead. Our experiments on high resolution real-world images and videos show that tiled prompts bring consistent gains in perceptual quality and fidelity, while reducing hallucinations and tile-level artifacts that can be found in global-prompt baselines. Project Page: https://bryanswkim.github.io/tiled-prompts/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03342 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution Kim, Bryan Sangwoo Park, Jonghyun Ye, Jong Chul Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Text-conditioned diffusion models have advanced image and video super-resolution by using prompts as semantic priors, and modern super-resolution pipelines typically rely on latent tiling to scale to high resolutions. In practice, a single global caption is used with the latent tiling, often causing prompt misguidance. Specifically, a coarse global prompt often misses localized details (errors of omission) and provides locally irrelevant guidance (errors of commission) which leads to substandard results at the tile level. To solve this, we propose Tiled Prompts, a unified framework for image and video super-resolution that generates a tile-specific prompt for each latent tile and performs super-resolution under locally text-conditioned posteriors to resolve prompt misguidance with minimal overhead. Our experiments on high resolution real-world images and videos show that tiled prompts bring consistent gains in perceptual quality and fidelity, while reducing hallucinations and tile-level artifacts that can be found in global-prompt baselines. Project Page: https://bryanswkim.github.io/tiled-prompts/. |
| title | Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.03342 |