Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
NeuDonatello: Uncertainty-Aware Framework for Accurate Neural SDF Learning
Alvin Jinsung Choi, Wanhee Kim, Taeyun Kim +3
Neural surface reconstruction has emerged as a powerful paradigm for recovering high-quality 3D surfaces from multi-view images. However, recovering accurate geometry solely from R…
cs.CV2026
Contextrast++: Robust Multi-Scale Contextual Contrastive Learning for Semantic Segmentation
Changki Sung, Hyungtae Lim, Wanhee Kim +2
Semantic segmentation has rapidly advanced with deep learning; however, challenges remain in effectively capturing local and global contexts as well as addressing the long-tailed d…
cs.CV2024
Contextrast: Contextual Contrastive Learning for Semantic Segmentation
Changki Sung, Wanhee Kim, Jungho An +3
Despite great improvements in semantic segmentation, challenges persist because of the lack of local/global contexts and the relationship between them. In this paper, we propose Co…