Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval
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_ | 1866914352736501760 |
|---|---|
| author | Chen, Yuan-Chih Lu, Chun-Shien |
| author_facet | Chen, Yuan-Chih Lu, Chun-Shien |
| contents | Recent advances in image authenticity have primarily focused on deepfake detection and localization, leaving recovery of tampered contents for factual retrieval relatively underexplored. We propose a unified hidden-code recovery framework that enables both retrieval and restoration from post-hoc and in-generation watermarking paradigms. Our method encodes semantic and perceptual information into a compact hidden-code representation, refined through multi-scale vector quantization, and enhances contextual reasoning via conditional Transformer modules. To enable systematic evaluation for natural images, we construct ImageNet-S, a benchmark that provides paired image-label factual retrieval tasks. Extensive experiments on ImageNet-S demonstrate that our method exhibits promising retrieval and reconstruction performance while remaining fully compatible with diverse watermarking pipelines. This framework establishes a foundation for general-purpose image recovery beyond detection and localization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22759 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval Chen, Yuan-Chih Lu, Chun-Shien Computer Vision and Pattern Recognition Recent advances in image authenticity have primarily focused on deepfake detection and localization, leaving recovery of tampered contents for factual retrieval relatively underexplored. We propose a unified hidden-code recovery framework that enables both retrieval and restoration from post-hoc and in-generation watermarking paradigms. Our method encodes semantic and perceptual information into a compact hidden-code representation, refined through multi-scale vector quantization, and enhances contextual reasoning via conditional Transformer modules. To enable systematic evaluation for natural images, we construct ImageNet-S, a benchmark that provides paired image-label factual retrieval tasks. Extensive experiments on ImageNet-S demonstrate that our method exhibits promising retrieval and reconstruction performance while remaining fully compatible with diverse watermarking pipelines. This framework establishes a foundation for general-purpose image recovery beyond detection and localization. |
| title | Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.22759 |