When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry
2026-07-20 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors point out that current methods to spot edited parts of images mainly look at flat 2D clues, which can fail when the edits blend very well with the rest of the picture. To improve this, they use 3D information like depth and surface angles obtained from a single image, but carefully pick only the reliable parts since these 3D cues can be noisy. Their new system, GFrame, combines trustworthy 3D and 2D clues to better find subtle edits in images. Tests show their approach works well even with limited resources, suggesting 3D geometry can add useful evidence beyond traditional methods.
image manipulation localization2D forensic cuesgeometric reasoningmonocular reconstructiondepth estimationsurface normalsfeature fusionfine-grained localizationnoisy geometryRGB features
Authors
Guofeng Yu, Zhiqing Guo, Dan Ma, Gaobo Yang
Abstract
Existing image manipulation localization (IML) methods rely heavily on 2D forensic cues, such as low-level artifacts, noise traces, and semantic inconsistencies in the manipulated image. While effective in many cases, these cues become much less discriminative when manipulated regions are well blended with their surrounding context in appearance. In such cases, a manipulated region may remain locally appearance-consistent, but still violate the geometric structure of the surrounding scene. This limitation motivates us to go beyond purely 2D evidence and introduce geometric reasoning into IML. To this end, we leverage monocular reconstruction to obtain auxiliary geometric cues, including depth and surface normals. However, a key challenge lies in the fact that reconstructed geometry on manipulated images is inherently noisy and cannot be used naively. Rather than treating depth and normals as direct evidence, we estimate their reliability and exploit them selectively for localization. Based on this principle, we design a geometry-aware framework (GFrame) that fuses reliable geometric cues with RGB features and propagates them across scales to improve fine-grained localization. Extensive experiments show that the proposed method achieves excellent performance under limited budget constraints. These results indicate that reliable 3D geometry provides complementary forensic evidence beyond traditional 2D cues for IML. Related code will be released.