Paper deep dive
Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method
Haofei Xu, Wei Cheng, Sizhe Li, Jie Xiong
Intelligence
Status: succeeded | Model: Gemma-4-26B-A4B | Prompt: intel-v1 | Confidence: 93%
Last extracted: 7/13/2026, 3:32:34 AM
Summary
The paper proposes a Conditional Rectified Flow-based end-to-end rapid seismic inversion method. It utilizes a dedicated seismic encoder for multi-scale feature extraction and a layer-by-layer injection control strategy for fine-grained conditional control. The method demonstrates superior sampling efficiency compared to Diffusion models and higher accuracy than InversionNet on the OpenFWI benchmark, while also showing zero-shot generalization capabilities on Marmousi real data to alleviate initial model dependency in Full Waveform Inversion (FWI).
Entities (8)
Relation Signals (7)
Haofei Xu → authored → Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method
confidence 99% · Authors: Haofei Xu, Wei Cheng, Sizhe Li, Jie Xiong
Proposed Method → evaluatedon → OpenFWI
confidence 95% · Experimental results demonstrate that the proposed method achieves excellent inversion accuracy on the OpenFWI benchmark dataset.
Conditional Rectified Flow → usedin → Seismic Inversion
confidence 95% · This paper proposes an end-to-end fast seismic inversion method based on Conditional Rectified Flow
Seismic Encoder → extracts → Multi-scale seismic features
confidence 90% · designs a dedicated seismic encoder to extract multi-scale seismic features
Proposed Method → generalizesto → Marmousi
confidence 90% · Our zero-shot generalization experiments on Marmousi real data further verify the practical value of the method.
Proposed Method → outperforms → InversionNet
confidence 90% · compared with InversionNet methods, it achieves higher accuracy in generation.
Proposed Method → outperforms → Diffusion
confidence 90% · Compared with Diffusion methods, it achieves sampling acceleration
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
Abstract:Seismic inversion is a core problem in geophysical exploration, where traditional methods suffer from high computational costs and are susceptible to initial model dependence. In recent years, deep generative model-based seismic inversion methods have achieved remarkable progress, but existing generative models struggle to balance sampling efficiency and inversion accuracy. This paper proposes an end-to-end fast seismic inversion method based on Conditional Rectified Flow[1], which designs a dedicated seismic encoder to extract multi-scale seismic features and adopts a layer-by-layer injection control strategy to achieve fine-grained conditional control. Experimental results demonstrate that the proposed method achieves excellent inversion accuracy on the OpenFWI[2] benchmark dataset. Compared with Diffusion[3,4] methods, it achieves sampling acceleration; compared with InversionNet[5,6,7] methods, it achieves higher accuracy in generation. Our zero-shot generalization experiments on Marmousi[8,9] real data further verify the practical value of the method. Experimental results show that the proposed method achieves excellent inversion accuracy on the OpenFWI benchmark dataset; compared with Diffusion methods, it achieves sampling acceleration while maintaining higher accuracy than InversionNet methods; experiments based on the Marmousi standard model further verify that this method can generate high-quality initial velocity models in a zero-shot manner, effectively alleviating the initial model dependency problem in traditional Full Waveform Inversion (FWI), and possesses industrial practical value.
Tags
Links
- Source: https://arxiv.org/abs/2603.15354v1
- Canonical: https://arxiv.org/abs/2603.15354v1
Trouble viewing inline? Open PDF directly →
Full Text
4,934 characters extracted from source content.
Expand or collapse full text
Skip to main content arXiv is now an independent nonprofit! Learn more × Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2603.15354v1 (cs) [Submitted on 16 Mar 2026] Title:Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method Authors:Haofei Xu, Wei Cheng, Sizhe Li, Jie Xiong View a PDF of the paper titled Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method, by Haofei Xu and 3 other authors View PDF Abstract:Seismic inversion is a core problem in geophysical exploration, where traditional methods suffer from high computational costs and are susceptible to initial model dependence. In recent years, deep generative model-based seismic inversion methods have achieved remarkable progress, but existing generative models struggle to balance sampling efficiency and inversion accuracy. This paper proposes an end-to-end fast seismic inversion method based on Conditional Rectified Flow[1], which designs a dedicated seismic encoder to extract multi-scale seismic features and adopts a layer-by-layer injection control strategy to achieve fine-grained conditional control. Experimental results demonstrate that the proposed method achieves excellent inversion accuracy on the OpenFWI[2] benchmark dataset. Compared with Diffusion[3,4] methods, it achieves sampling acceleration; compared with InversionNet[5,6,7] methods, it achieves higher accuracy in generation. Our zero-shot generalization experiments on Marmousi[8,9] real data further verify the practical value of the method. Experimental results show that the proposed method achieves excellent inversion accuracy on the OpenFWI benchmark dataset; compared with Diffusion methods, it achieves sampling acceleration while maintaining higher accuracy than InversionNet methods; experiments based on the Marmousi standard model further verify that this method can generate high-quality initial velocity models in a zero-shot manner, effectively alleviating the initial model dependency problem in traditional Full Waveform Inversion (FWI), and possesses industrial practical value. Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.15354 [cs.LG] (or arXiv:2603.15354v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2603.15354 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Haofei Xu [view email] [v1] Mon, 16 Mar 2026 14:36:28 UTC (2,868 KB) Full-text links: Access Paper: View a PDF of the paper titled Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method, by Haofei Xu and 3 other authorsView PDF view license Current browse context: cs.LG < prev | next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?) mathjaxToggle(); We gratefully acknowledge support from our major funders, member institutions, , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from