Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning
Jian Shi, Michael Birsak, Wenqing Cui +2
This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectiv…
cs.CV2025
MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models
Michael Birsak, John Femiani, Biao Zhang +1
Assigning realistic materials to 3D models remains a significant challenge in computer graphics. We propose MatCLIP, a novel method that extracts shape- and lighting-insensitive de…