Flow-matching models generate high-quality images and videos, but repeated neural network evaluations make sampling expensive. Skipping evaluations reduces this cost by extending an available velocity estimate over a longer span. However, local velocity agreement alone does not determine a suitable span, and checking e...
Xuan-Hua Yin, Chuanzhi Xu, Hao-Xian Zhou et al.· 0 citations
Scientific figure assessment in peer review differs fundamentally from general image quality evaluation: a figure must be visually legible, faithfully support the manuscript's claims, and communicate evidence with a clear visual hierarchy. However, if we apply traditional image assessment methods to scientific figure q...
Chuanzhi Xu, Zihan Deng, Huiqi Liang et al.· 0 citations
This work introduces VirSqueezer, a framework designed to generate both localized deformations and complex squeezing dynamics, such as rupture and overflow, and enables the generation of physically realistic visual effects directly from continuous, fine-grained squeezing control signals.
Qian Zhang, Xiao-Ming Chen, Xiao-Rui Ma et al.· 0 citations
FracEvent, an event simulator that models this pixel-level lifecycle with fractional-relaxation voltage dynamics, improves the temporal structure of generated events and achieves stronger downstream-transfer results than competing simulator baselines, showing its practical value for event-camera simulation.
