2 papers
cs.CV2026
ViT-Up: Faithful Feature Upsampling for Vision Transformers
Krispin Wandel, Jingchuan Wang, Hesheng Wang
Vision Transformers (ViTs) have become a dominant architecture for visual representation learning, providing exceptionally strong and broadly reusable backbone features. However, V…
cs.CV2025
SemAlign3D: Semantic Correspondence between RGB-Images through Aligning 3D Object-Class Representations
Krispin Wandel, Hesheng Wang
Semantic correspondence made tremendous progress through the recent advancements of large vision models (LVM). While these LVMs have been shown to reliably capture local semantics,…