47 citations · 63 across the 10 of their papers we have counts for
5 papers · 1 filter
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…
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…
InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions
Qian Wang, Biao Zhang, Michael Birsak +1
Recent works have explored text-guided image editing using diffusion models and generated edited images based on text prompts. However, the models struggle to accurately locate the…
MDP: A Generalized Framework for Text-Guided Image Editing by Manipulating the Diffusion Path
Qian Wang, Biao Zhang, Michael Birsak +1
Image generation using diffusion can be controlled in multiple ways. In this paper, we systematically analyze the equations of modern generative diffusion networks to propose a fra…
BlobGAN-3D: A Spatially-Disentangled 3D-Aware Generative Model for Indoor Scenes
Qian Wang, Yiqun Wang, Michael Birsak +1
3D-aware image synthesis has attracted increasing interest as it models the 3D nature of our real world. However, performing realistic object-level editing of the generated images…