# RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization

arXiv: https://arxiv.org/abs/2508.09459 · HTML: https://mlsanity.com/paper/2508.09459/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Focal Self-attention for Local-Global Interactions in Vision Transformers](https://mlsanity.com/paper/2107.00641/) (2021)
- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2103.10596/) (2021)
- [TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization](https://mlsanity.com/paper/2212.10957/) (2022)
- [Towards An End-to-End Framework for Flow-Guided Video Inpainting](https://mlsanity.com/paper/2204.02663/) (2022)
- [Image Manipulation Detection by Multi-View Multi-Scale Supervision](https://mlsanity.com/paper/2104.06832/) (2021)
- [FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting](https://mlsanity.com/paper/2109.02974/) (2021)
- [Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2108.12947/) (2021)
- [ObjectFormer for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2203.14681/) (2022)
- [Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning](https://mlsanity.com/paper/2311.11077/) (2023)
- [Onion-Peel Networks for Deep Video Completion](https://mlsanity.com/paper/1908.08718/) (2019)
- [IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization](https://mlsanity.com/paper/2406.10580/) (2024)
- [Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization](https://mlsanity.com/paper/2412.13753/) (2024)
- [Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer](https://mlsanity.com/paper/2412.14598/) (2024)
- [Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning](https://mlsanity.com/paper/2309.14900/) (2023)
- [Rethinking Image Forgery Detection via Soft Contrastive Learning and Unsupervised Clustering](https://mlsanity.com/paper/2308.09307/) (2023)
- [Deep Video Inpainting Detection](https://mlsanity.com/paper/2101.11080/) (2021)
- [VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces](https://mlsanity.com/paper/2211.15775/) (2022)
- [Omni-IML: Towards Unified Image Manipulation Localization](https://mlsanity.com/paper/2411.14823/) (2024)
- [UVL2: A Unified Framework for Video Tampering Localization](https://mlsanity.com/paper/2309.16126/) (2023)
- [Video Inpainting Localization with Contrastive Learning](https://mlsanity.com/paper/2406.17628/) (2024)

## Abstract (arXiv)

Visual manipulation localization (VML) aims to identify tampered regions in images and videos, a task that has become increasingly challenging with the rise of advanced editing tools. Existing methods face two central issues. The first is resolution diversity. Resizing or padding can distort subtle forensic cues and introduce unnecessary computational cost. The second is the difficulty of extending spatial models for images to spatio-temporal inputs in videos, which often results in maintaining separate architectures for the two data types. To address these challenges, we propose RelayFormer, a unified framework that adapts to varying resolutions and naturally handles both static and temporal visual data. RelayFormer partitions inputs into fixed-size sub-images and introduces Global Local Relay (GLR) tokens that propagate structured context through a relay-based attention mechanism. This design enables efficient exchange of global cues, such as semantic or temporal consistency, while preserving fine-grained manipulation artifacts. Unlike prior approaches that depend on uniform resizing or sparse attention, RelayFormer scales to variable resolutions and video sequences with minimal overhead. Experiments across diverse benchmarks demonstrate superior performance and strong efficiency, combining resolution adaptivity without interpolation or excessive padding, unified processing for images and videos, and a favorable balance between accuracy and computational cost. Code is available at~hrefhttps://github.com/WenOOI/RelayFormerhttps://github.com/WenOOI/RelayFormer.