TPIE: Topology-Preserved Image Editing With Text Instructions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jayakumar, Nivetha, Gadila, Srivardhan Reddy, Hossain, Tonmoy, Ji, Yangfeng, Zhang, Miaomiao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912132712366080
author Jayakumar, Nivetha
Gadila, Srivardhan Reddy
Hossain, Tonmoy
Ji, Yangfeng
Zhang, Miaomiao
author_facet Jayakumar, Nivetha
Gadila, Srivardhan Reddy
Hossain, Tonmoy
Ji, Yangfeng
Zhang, Miaomiao
contents Preserving topological structures is important in real-world applications, particularly in sensitive domains such as healthcare and medicine, where the correctness of human anatomy is critical. However, most existing image editing models focus on manipulating intensity and texture features, often overlooking object geometry within images. To address this issue, this paper introduces a novel method, Topology-Preserved Image Editing with text instructions (TPIE), that for the first time ensures the topology and geometry remaining intact in edited images through text-guided generative diffusion models. More specifically, our method treats newly generated samples as deformable variations of a given input template, allowing for controllable and structure-preserving edits. Our proposed TPIE framework consists of two key modules: (i) an autoencoder-based registration network that learns latent representations of object transformations, parameterized by velocity fields, from pairwise training images; and (ii) a novel latent conditional geometric diffusion (LCDG) model efficiently capturing the data distribution of learned transformation features conditioned on custom-defined text instructions. We validate TPIE on a diverse set of 2D and 3D images and compare them with state-of-the-art image editing approaches. Experimental results show that our method outperforms other baselines in generating more realistic images with well-preserved topology. Our code will be made publicly available on Github.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16714
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TPIE: Topology-Preserved Image Editing With Text Instructions
Jayakumar, Nivetha
Gadila, Srivardhan Reddy
Hossain, Tonmoy
Ji, Yangfeng
Zhang, Miaomiao
Computer Vision and Pattern Recognition
Preserving topological structures is important in real-world applications, particularly in sensitive domains such as healthcare and medicine, where the correctness of human anatomy is critical. However, most existing image editing models focus on manipulating intensity and texture features, often overlooking object geometry within images. To address this issue, this paper introduces a novel method, Topology-Preserved Image Editing with text instructions (TPIE), that for the first time ensures the topology and geometry remaining intact in edited images through text-guided generative diffusion models. More specifically, our method treats newly generated samples as deformable variations of a given input template, allowing for controllable and structure-preserving edits. Our proposed TPIE framework consists of two key modules: (i) an autoencoder-based registration network that learns latent representations of object transformations, parameterized by velocity fields, from pairwise training images; and (ii) a novel latent conditional geometric diffusion (LCDG) model efficiently capturing the data distribution of learned transformation features conditioned on custom-defined text instructions. We validate TPIE on a diverse set of 2D and 3D images and compare them with state-of-the-art image editing approaches. Experimental results show that our method outperforms other baselines in generating more realistic images with well-preserved topology. Our code will be made publicly available on Github.
title TPIE: Topology-Preserved Image Editing With Text Instructions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.16714