ThinGPT: describing sedimentary rock thin section images with a multimodal large language model
Authors:
- Xin LuoXLXin Luo
- Jian-Meng SunJSJian-Meng Sun
- Peng ChiPCPeng Chi
- Ran ZhangRZRan Zhang
- Rui-Kang CuiRCRui-Kang Cui
- Xing-Hua CiXCXing-Hua Ci
- Wei LiuWLWei Liu
Open Access
- 1 December 2025
- journal article
- Published by KEAI Publishing in Petroleum Science
- Vol. 22 (12) , 5020-5033
Abstract
No abstract availableFunding Information
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China (42174143)
This publication has 30 references indexed in Scilit:
- ClipSAM: CLIP and SAM collaboration for zero-shot anomaly segmentationNeurocomputing, 2024
- Control and prediction of bedding-parallel fractures in fine-grained sedimentary rocks: A case from the Permian Lucaogou Formation in Jimusar Sag, Junggar Basin, Western ChinaPetroleum Science, 2024
- EntroCap: Zero-shot image captioning with entropy-based retrievalNeurocomputing, 2024
- A multi-condition denoising diffusion probabilistic model controls the reconstruction of 3D digital rocksComputers & Geosciences, 2024
- Determining the best feature combination through text and probabilistic feature analysis for GPT-2-based mobile app review detectionApplied Intelligence, 2023
- Quantitative characterization of tight gas sandstone reservoirs using seismic data via an integrated rock-physics-based frameworkPetroleum Science, 2023
- CLIP-Adapter: Better Vision-Language Models with Feature AdaptersInternational Journal of Computer Vision, 2023
- Enhancement of thin-section image using super-resolution method with application to the mineral segmentation and classification in tight sandstone reservoirJournal of Petroleum Science and Engineering, 2022
- Application of deep learning for semantic segmentation of sandstone thin sectionsComputers & Geosciences, 2021
- Rock thin sections identification based on improved squeeze-and-Excitation Networks modelComputers & Geosciences, 2021