3 papers
cs.CV2026
SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing
Haowang Cui, Rui Chen, Tao Luo +3
Training-free image editing has recently attracted increasing attention due to its ability to modify real images using powerful pre-trained diffusion and flow-matching models witho…
cs.CV2025
Towards Imperceptible JPEG Image Hiding: Multi-range Representations-driven Adversarial Stego Generation
Junxue Yang, Xin Liao, Weixuan Tang +2
Image hiding fully explores the hidden potential of deep learning-based models, aiming to conceal image-level messages within cover images and reveal them from stego images to achi…
cs.CV2024
Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics
Xiaoshuai Wu, Xin Liao, Bo Ou +2
AI-generated content has accelerated the topic of media synthesis, particularly Deepfake, which can manipulate our portraits for positive or malicious purposes. Before releasing th…