ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation

arXiv:2511.14259 · cs.CV · Submitted 2025-11-18 · Read on arXiv

cs.CV

Submitted: 2025-11-18

Updated: 2026-10-13

Code: https://github.com/timothybrooks/instruct-pix2pix

Terminology

• Benchmark — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Qwen2.5-VL Technical Report
• Diffusion Deepfake
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Hidden in plain sight: VLMs overlook their visual representations
• HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
• ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
• InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control
• DeepSeek-VL: Towards Real-World Vision-Language Understanding
• Ovis2.5 Technical Report
• Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods
• ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling
• SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
• Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Models
• Can VLMs Detect and Localize Fine-Grained AI-Edited Images?
• Taming Rectified Flow for Inversion and Editing
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• Qwen-Image Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models