8 papers
Geodesic-informed Generative Diffusion Model For Topology-preserved Image Video Generation
Nian Wu, Nivetha Jayakumar, Jiarui Xing +1
Generative diffusion models have emerged as a class of powerful techniques for various imaging applications, including but not limited to synthesis, reconstruction, and segmentatio…
FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation
Ming Hu, Jianfu Yin, Mingyu Dou +5
In-Context Segmentation (ICS) aims to precisely segment arbitrary semantic concepts, such as objects or parts, given one or a few annotated visual exemplars. In this paper, we revi…
WhereEdit: Mask-aware Local Latent Editing for One-Step Image Editing
Ming Hu, Mingyu Dou, Jianfu Yin +5
Recent one-step text-to-image (T2I) models enable efficient image synthesis and provide new opportunities for real-time image editing. However, existing one-step editing methods pr…
4DLoG: Generative Modeling of Neurodegenerative Brain Anatomy with 4D Longitudinal Diffusion Model
Nivetha Jayakumar, Swakshar Deb, Bahram Jafrasteh +2
Modeling and predicting neurodegenerative disease progression from medical images remains a major challenge in medical AI, with significant implications for early diagnosis, diseas…
Unsupervised Cardiac Video Translation Via Motion Feature Guided Diffusion Model
Swakshar Deb, Nian Wu, Frederick H. Epstein +1
This paper presents a novel motion feature guided diffusion model for unpaired video-to-video translation (MFD-V2V), designed to synthesize dynamic, high-contrast cine cardiac magn…
IGG: Image Generation Informed by Geodesic Dynamics in Deformation Spaces
Nian Wu, Nivetha Jayakumar, Jiarui Xing +1
Generative models have recently gained increasing attention in image generation and editing tasks. However, they often lack a direct connection to object geometry, which is crucial…
Learning Geodesics of Geometric Shape Deformations From Images
Nian Wu, Miaomiao Zhang
This paper presents a novel method, named geodesic deformable networks (GDN), that for the first time enables the learning of geodesic flows of deformation fields derived from imag…
Interior Object Geometry via Fitted Frames
Stephen M. Pizer, Zhiyuan Liu, Junjie Zhao +6
We propose a means of computing fitted frames on the boundary and in the interior of objects and using them to provide the basis for producing geometric features from them that are…