4 papers
Engram-E2VID: Reference-Based Event-to-Video Reconstruction via Generative Activation of Appearance Engrams
Feiyu Ji, Xiang Li, Hao Ma +6
Reference-based event-to-video reconstruction aims to recover target RGB frames from a reference frame and the event stream captured over the reference-to-target interval. Although…
FS-DVS: A Frequency-Selective Dynamic Visual Sensing Paradigm for Enhancing Information Completeness
Feiyu Ji, Xiaokang Yang, Xiaoyun Yuan
Dynamic vision sensors (DVS) offer exceptional temporal resolution and dynamic range by asynchronously reporting pixel-level intensity changes. However, conventional DVS rely on a…
FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
Junyi Wu, Zhiteng Li, Haotong Qin +2
Text-guided image editing with diffusion models has achieved remarkable quality but often suffers from prohibitive latency. We introduce \textbf{FlashEdit}, a real-time localized i…
Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark
Yi Xin, Jianjiang Yang, Siqi Luo +10
Pre-trained vision models (PVMs) have demonstrated remarkable adaptability across a wide range of downstream vision tasks, showcasing exceptional performance. However, as these mod…