9 papers
LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation
Guanjie Wang, Zehua Ma, Han Fang +1
The rapid progress of image-guided video generation (I2V) has raised concerns about its potential misuse in misinformation and fraud, underscoring the urgent need for effective dig…
Flow of Truth: Proactive Temporal Forensics for Image-to-Video Generation
Yuzhuo Chen, Zehua Ma, Han Fang +3
The rapid rise of image-to-video (I2V) generation enables realistic videos to be created from a single image but also brings new forensic demands. Unlike static images, I2V content…
Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiation
Hengyi Wang, Ruiqiang Zhang, Chang Liu +4
With the rising need for spatially grounded tasks such as Vision-Language Navigation/Action, allocentric perception capabilities in Vision-Language Models (VLMs) are receiving grow…
FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection
Ruiqiang Zhang, Hengyi Wang, Chang Liu +3
Large-scale text-to-image (T2I) diffusion models excel at open-domain synthesis but still struggle with precise text rendering, especially for multi-line layouts, dense typography,…
LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer
Yuzhuo Chen, Zehua Ma, Jianhua Wang +3
In controllable image synthesis, generating coherent and consistent images from multiple references with spatial layout awareness remains an open challenge. We present LAMIC, a Lay…
TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity
Yuzhuo Chen, Zehua Ma, Han Fang +2
AI-generated content (AIGC) enables efficient visual creation but raises copyright and authenticity risks. As a common technique for integrity verification and source tracing, digi…