Papers › Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image...

Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization

18 Dec 2024arXiv:2412.13753archive 2025-07-28

Xuekang Zhu, Xiaochen Ma, Lei Su, Zhuohang Jiang, Bo Du, Xiwen Wang, Zeyu Lei, Wentao Feng, Chi-Man Pun, Jizhe Zhou

The mesoscopic level serves as a bridge between the macroscopic and microscopic worlds, addressing gaps overlooked by both. Image manipulation localization (IML), a crucial technique to pursue truth from fake images, has long relied on low-level (microscopic-level) traces. However, in practice, most tampering aims to deceive the audience by altering image semantics. As a result, manipulation commonly occurs at the object level (macroscopic level), which is equally important as microscopic traces. Therefore, integrating these two levels into the mesoscopic level presents a new perspective for IML research. Inspired by this, our paper explores how to simultaneously construct mesoscopic representations of micro and macro information for IML and introduces the Mesorch architecture to orchestrate both. Specifically, this architecture i) combines Transformers and CNNs in parallel, with Transformers extracting macro information and CNNs capturing micro details, and ii) explores across different scales, assessing micro and macro information seamlessly. Additionally, based on the Mesorch architecture, the paper introduces two baseline models aimed at solving IML tasks through mesoscopic representation. Extensive experiments across four datasets have demonstrated that our models surpass the current state-of-the-art in terms of performance, computational complexity, and robustness.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

scu-zjz/Mesorch officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ManipulationImage Manipulation Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Manipulation Localization CASIAv1(Protoclo-CAT) Mesorch Pixel Binary F1 0.8397 #1 of 8 Archive leaderboard report
Image Manipulation Localization COVERAGE(Protocol-CAT) Mesorch Pixel Binary F1 0.5862 #2 of 8 Archive leaderboard report
Image Manipulation Localization Columbia(Protocol-CAT) Mesorch Pixel Binary F1 0.9224 #2 of 8 Archive leaderboard report
Image Manipulation Localization NIST16(Protocol-CAT) Mesorch Pixel Binary F1 0.3921 #2 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections