# Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval

Source: [Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval](<https://www.sota2.com/research/paper/69a124ec2d603e6de3e3c347>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-28T05:00:04.461Z

Authors: Yuan-Chih Chen, Chun-Shien Lu

Published: 2026-02-26T08:47:48.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.22759>)

[PDF](<https://arxiv.org/pdf/2602.22759.pdf>)