VICR: Visual In-Context Restoration for Real-World Image Super-Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910276203315200 |
|---|---|
| author | Zhang, Qichang Wang, Hailong Li, Baiang Wang, Linhao Fu, Rong Cheng, Erkang Fong, Simon James |
| author_facet | Zhang, Qichang Wang, Hailong Li, Baiang Wang, Linhao Fu, Rong Cheng, Erkang Fong, Simon James |
| contents | Real-world image super-resolution (Real-ISR) requires balancing structural fidelity to degraded observations with realistic detail synthesis. However, existing generative Real-ISR methods often rely on entangled conditioning mechanisms, leading to structural drift or semantically inconsistent details. To address this issue, we propose Visual In-Context Restoration (VICR), a Diffusion Transformer (DiT)-based framework that formulates Real-ISR as image completion. Specifically, we introduce a decoupled visual prior injection mechanism that derives local and global cues from the low-quality (LQ) image: local cues help recover image structures and support high-frequency detail synthesis, while global cues guide overall generation and promote semantic consistency. For ambiguous regions under severe degradation, VICR employs an inference-time agent to refine semantic prompts using visual evidence from the LQ input while keeping model parameters fixed. Experiments show that VICR achieves state-of-the-art performance across multiple Real-ISR benchmarks with only 127M trainable parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00704 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VICR: Visual In-Context Restoration for Real-World Image Super-Resolution Zhang, Qichang Wang, Hailong Li, Baiang Wang, Linhao Fu, Rong Cheng, Erkang Fong, Simon James Computer Vision and Pattern Recognition Real-world image super-resolution (Real-ISR) requires balancing structural fidelity to degraded observations with realistic detail synthesis. However, existing generative Real-ISR methods often rely on entangled conditioning mechanisms, leading to structural drift or semantically inconsistent details. To address this issue, we propose Visual In-Context Restoration (VICR), a Diffusion Transformer (DiT)-based framework that formulates Real-ISR as image completion. Specifically, we introduce a decoupled visual prior injection mechanism that derives local and global cues from the low-quality (LQ) image: local cues help recover image structures and support high-frequency detail synthesis, while global cues guide overall generation and promote semantic consistency. For ambiguous regions under severe degradation, VICR employs an inference-time agent to refine semantic prompts using visual evidence from the LQ input while keeping model parameters fixed. Experiments show that VICR achieves state-of-the-art performance across multiple Real-ISR benchmarks with only 127M trainable parameters. |
| title | VICR: Visual In-Context Restoration for Real-World Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.00704 |