Skip to content
Review

GIFTBench: Diagnosing Generalization in Image Forgery Localization and Informing Model Design

Oct 2026 · 0 citations · 41 references
Computer Science

TL;DR

This work introduces GIFTBench, a multi-axis benchmark of 115,013 manipulated images with pixel-level annotations spanning manipulation source, semantic target, editing operation, and composition complexity, and develops ForenScope, a detection and localization framework combining classification-adapted representations with multi-depth, multi-scale spatial features, learned layer fusion, and selective coarse-scale conditioning.

Abstract

Reliable evaluation of image forgery localization (IFL) requires assessing models under diverse distribution changes, yet existing benchmarks often cover limited manipulation conditions or entangle multiple factors in cross-dataset evaluation. Consequently, aggregate performance provides an incomplete view of localization generalization. We introduce GIFTBench, a multi-axis benchmark of 115,013 manipulated images with pixel-level annotations spanning manipulation source, semantic target, editing operation, and composition complexity. GIFTBench supports axis-specific transfer analysis and evaluation on twelve external datasets. Its diagnostic studies reveal asymmetric cross-source transfer, recall-dominated failures, and heterogeneous degradation across semantic, operational, and compositional changes. Beyond diagnosis, the scale and diversity of GIFTBench provide a substantially broader training distribution than conventional IFL datasets. Training representative localizers on GIFTBench consistently improves their aggregate transfer to external datasets, showing that the benchmark serves not only as an evaluation tool but also as an effective training resource for cross-domain localization. Guided by the diagnostic findings, we further develop ForenScope, a detection and localization framework combining classification-adapted representations with multi-depth, multi-scale spatial features, learned layer fusion, and selective coarse-scale conditioning. Experiments show improved cross-dataset localization while retaining image-level detection capability. The GIFTBench dataset showcase page is available at https://giftbench-preview.doudoudouya337.chatgpt.site.

View source

Similar papers

Sep 2026

Evaluating the Evaluators: Diagnosing Large Multimodal Models for AI-Generated Image Assessment

This work introduces SQUARE-Bench, a comprehensive benchmark that systematically evaluates LMM capabilities as evaluators of AI-generated images across four aspects: Semantics, Quality, Authenticity, and Responsibility, and conducts a proof-of-concept study of LMM-guided iterative editing.

Yu Zhao, Jia-Rui Wang, Hui-Yu Duan et al. · 0 citations
Sep 2026

Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images

Localizing AI-edited regions is essential for interpretable forensic analysis, but remains challenging due to subtle and spatially distributed artifacts that are misaligned with semantic or object boundaries. Existing approaches rely on pixel-level supervision from controlled editing pipelines, which is difficult to sc...

Junhee Lee, Donghyeon Jeon, Taeoh Kim et al. · 0 citations
Book Open access Sep 2026

UNMATCH: Selective Unbalanced Token–Patch Matching for Forensic Image–Claim Verification

Contextual image misuse pairs an image with a misleading claim. We study image–claim correspondence in fact-checked pairs containing out-of-context reuse, visual manipulation, or both. Existing pair-based detectors often compress the two modalities into a global compatibility score or learn a highly flexible interactio...

Xin-Jin Li, Lian Lian, Yuan-Zhe Yang et al. · 0 citations
Book Open access Nov 2026

BiPro-Net: Boundary-Aware Dual-Prototype Network for Robust Image Inpainting Detection

Image inpainting detection remains a major challenge in visual forensics, especially as modern tampering techniques produce increasingly realistic results, making the already subtle traces even harder to capture. Existing methods exploit diverse forensic cues but often rely on local feature aggregation or implicit bina...

Li-Zhi Xiong, Yu-Di Yuan, G. Xie et al. · 0 citations
Preprint Oct 2026

DimFlow: Bidirectional Grid-Expert Learning for Dynamic Gaussian Reconstruction

Dynamic Gaussian reconstruction requires compact scene features to support coordinated changes in geometry and appearance. A factorized grid provides efficient local queries, but accurate interpolation alone does not ensure that the resulting dynamic attributes remain compatible across space and time. We introduce DimF...

Gabriel Adineera, Jinoh Kim · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.