2 papers
cs.CR2025
Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations
Yue Li, Linying Xue, Dongdong Lin +3
With the flourishing prosperity of generative models, manipulated facial images have become increasingly accessible, raising concerns regarding privacy infringement and societal tr…
cs.CV2025
Preserving Topological and Geometric Embeddings for Point Cloud Recovery
Kaiyue Zhou, Zelong Tan, Hongxiao Wang +2
Recovering point clouds involves the sequential process of sampling and restoration, yet existing methods struggle to effectively leverage both topological and geometric attributes…