8 papers
Benchmarking Cross-Domain Audio-Visual Deception Detection
Xiaobao Guo, Zitong Yu, Nithish Muthuchamy Selvaraj +3
Automated deception detection is crucial for assisting humans in accurately assessing truthfulness and identifying deceptive behavior. Conventional contact-based techniques, like p…
DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
Zihan Zhou, Shilin Lu, Shuli Leng +4
Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project o…
Does FLUX Already Know How to Perform Physically Plausible Image Composition?
Shilin Lu, Zhuming Lian, Zihan Zhou +3
Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections)…
MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment
Hao Zhou, Xiaobao Guo, Yuzhe Zhu +1
Propelled by the breakthrough in deep generative models, audio-to-image generation has emerged as a pivotal cross-modal task that converts complex auditory signals into rich visual…
Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts
Leyang Li, Shilin Lu, Yan Ren +1
Ensuring the ethical deployment of text-to-image models requires effective techniques to prevent the generation of harmful or inappropriate content. While concept erasure methods o…
Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
Shilin Lu, Zihan Zhou, Jiayou Lu +2
Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks dur…