Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal
Qinming Zhou, Chenxi Sun, Deyang Kong +6
Real-world object removal is challenging due to two key difficulties: the target object's non-local effects, such as shadows and reflections, which are difficult to model, and the…
cs.CV2026
From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation
Qin Lei, Jiang Zhong, Xin Xiao +2
Curvilinear object segmentation, including vessels and cracks, is challenging due to extreme spatial sparsity and topological fragility, where small local errors can cause severe s…