3 papers
cs.CV2025
DreaMontage: Arbitrary Frame-Guided One-Shot Video Generation
Jiawei Liu, Junqiao Li, Jiangfan Deng +11
The "one-shot" technique represents a distinct and sophisticated aesthetic in filmmaking. However, its practical realization is often hindered by prohibitive costs and complex real…
cs.CR2025
FPT-Noise: Dynamic Scene-Aware Counterattack for Test-Time Adversarial Defense in Vision-Language Models
Jia Deng, Jin Li, Zhenhua Zhao +1
Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent studies have revealed that VLM…
cs.CV2025
WAFT: Warping-Alone Field Transforms for Optical Flow
Yihan Wang, Jia Deng
We introduce Warping-Alone Field Transforms (WAFT), a simple and effective method for optical flow. WAFT is similar to RAFT but replaces cost volume with high-resolution warping, a…