4 papers
A Likely Geometry of Generative Models
Frederik Möbius Rygaard, Shen Zhu, Yinzhu Jin +2
The geometry of generative models serves as the basis for interpolation, model inspection, and more. Unfortunately, most generative models lack a principal notion of geometry witho…
Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model
Shen Zhu, Yinzhu Jin, Ifrah Zawar +1
We propose a diffusion model designed to generate point-based shape representations with correspondences. Traditional statistical shape models have considered point correspondences…
RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models
Shen Zhu, Yinzhu Jin, Tyler Spears +2
We propose image-to-image diffusion models that are designed to enhance the realism and details of generated brain images by introducing sharp edges, fine textures, subtle anatomic…
MedIL: Implicit Latent Spaces for Generating Heterogeneous Medical Images at Arbitrary Resolutions
Tyler Spears, Shen Zhu, Yinzhu Jin +2
In this work, we introduce MedIL, a first-of-its-kind autoencoder built for encoding medical images with heterogeneous sizes and resolutions for image generation. Medical images ar…