ViTARHeat: A Resolution-Agnostic, Wavelet-Enhanced Framework for High-Fidelity Inpainting Detection
Abstract
Digital media authenticity is threatened by sophisticated generative image inpainting models, especially diffusion-based ones. These tools allow malicious image removal or alteration, creating photorealistic effects that are invisible to the human eye. Inpainting detection methods based on Convolutional Neural Networks (CNNs) mostly require fixed-resolution inputs, which limits them. This forces high-resolution images to be downsampled, destroying the subtle, high-frequency artifacts and noise inconsistencies that are forgery’s traces. ViTARHeat, a dual-stream framework for downsizing, is introduced in this paper. ViTARHeat’s architecture combines two innovations.
Fields of Study & Subjects
Digital Media Forensic Detection
Generative Adversarial Networks and Image Synthesis
Advanced Steganography and Watermarking Techniques
Publication details
- Journal / source
- Advances in Artificial Intelligence and Machine Learning
- Volume
- 06
- Issue
- 01
- Pages
- 4977–4977
- Publication date
- 1 January 2026
- Language
- EN