SegEdit: image editing via semantic mask segmentation and shape injection within diffusion model
Authors:
- Ruikang LiuRLRuikang Liu
- Qingwen XieQXQingwen Xie
- Nan JiangNJNan Jiang
- Zha ChengZCZha Cheng
- Zhaohui YuanZYZhaohui Yuan
- Xiaohui HuangXHXiaohui Huang
- Mengfei DuanMDMengfei Duan
- 22 January 2026
- journal article
- Published by Elsevier in Expert Systems with Applications
- Vol. 310
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Jiangxi Province (20252BAC200183)
- Natural Science Foundation of Jiangxi Province (20252BAC200181)
- Education Department of Jiangxi Province (GJJ2400504)
- National Key Research and Development Program of China (2022YFB2602200)
- National Natural Science Foundation of China (62062034)
- National Natural Science Foundation of China (62563011)
- National Natural Science Foundation of China (62172160)
- National Natural Science Foundation of China (62463009)
- Double Thousand Plan of Jiangxi Province (JXSQ2023201010)
- Cultivating Plan Program for the Leader in Science and Technology of Yunnan Province (20244BCE5 2147)
- Cultivating Plan Program for the Leader in Science and Technology of Yunnan Province (20244BCE52164)
This publication has 4 references indexed in Scilit:
- Diffusion Model-Based Image Editing: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
- Multimodal Image Synthesis and Editing: The Generative AI EraIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- SRInpaintor: When Super-Resolution Meets Transformer for Image InpaintingIEEE Transactions on Computational Imaging, 2022
- CLIPScore: A Reference-free Evaluation Metric for Image Captioning2021