NSTL国家科技图书文献中心

1. Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems NSTL国家科技图书文献中心

Sojin Lee | Dogyun Park ... - 《Computer Vision - ECCV 2024,Part LIII》 - European Conference on Computer Vision - 2025, - 288～304 - 共17页

摘要：Recent studies on inverse* problems have* | range of inverse* problems. However, the existing* | Variational Inference (DAVI) that solves inverse problems | proposed posterior samplers that leverage the pre-trained | diffusion models as powerful priors. These attempts have

关键词： Inverse problems | Diffusion models | Posterior sampling

2. Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Prediction NSTL国家科技图书文献中心

Jeffrey Wen | Rizwan Ahmad ... - 《Computer Vision - ECCV 2024,Part LX》 - European Conference on Computer Vision - 2025, - 182～199 - 共18页

摘要：In imaging inverse* problems, one seeks to* | . Because such problems* are ill-posed, there is great* | recover an image from missing/corrupted measurements | motivation to quantify the uncertainty induced by the | measurement-and-recovery process. Motivated by applications

关键词： Inverse problems | Uncertainty quantification | Conformal prediction | Posterior sampling | MRI

3. Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems NSTL国家科技图书文献中心

Yasar Utku Alcalar | Mehmet Akcakaya - 《Computer Vision - ECCV 2024,Part LXXXIII》 - European Conference on Computer Vision - 2025, - 444～460 - 共17页

摘要： generative techniques for solving inverse* problems. Despite* | their success in a variety of inverse* problems in* | , application of these ideas for solving inverse* problems with* | various noisy inverse* problems, including Gaussian and* | Diffusion models have emerged as powerful

关键词： Diffusion models | Zero-Shot learning | Inverse problems | Plug-and-Play (PnP) methods | Unrolled networks | Bayesian methods

4. On the Problems of Convergence of Iterative Methods for Solving Two-Coefficient Inverse Problems of Ultrasound Tomography NSTL国家科技图书文献中心

Alexander Goncharsky | Sergey Romanov ... - 《Supercomputing,Part I》 - Russian Supercomputing Days Conference - 2025, - 111～125 - 共15页

摘要： inverse problems of wave tomography, namely, two | -coefficient inverse* problems of reconstruction of unknown* | This article explores the problems* of* | absorption in the inverse* problem. Model calculations on a* | convergence of iterative methods for solving nonlinear

关键词： Supercomputer simulations | High-performance scientific computing | Inverse problems | Ultrasound tomography | Nondestructive testing

5. Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems NSTL国家科技图书文献中心

Hyungjin Chung | Jong Chul Ye - 《Computer Vision - ECCV 2024,Part LXXV》 - European Conference on Computer Vision - 2025, - 432～455 - 共24页

摘要：Recent inverse* problem solvers that leverage* | seamless integration of 3D inverse* solvers and thus leads* | diffusion inverse* solvers even when training with gold* | generative diffusion priors have garnered significant | attention due to their exceptional quality. However

关键词： Diffusion models | Inverse problems | OOD adaptation

6. CoSIGN: Few-Step Guidance of ConSIstency Model to Solve General INverse Problems NSTL国家科技图书文献中心

Jiankun Zhao | Bowen Song ... - 《Computer Vision - ECCV 2024,Part XLVIII》 - European Conference on Computer Vision - 2025, - 108～126 - 共19页

摘要： strong priors for solving general inverse problems | . Most existing Diffusion model-based Inverse* Problem* | achieves new state-of-the-art in diffusion-based inverse | employing prior-based inverse* problem solvers for real* | Diffusion models have been demonstrated as

关键词： Inverse problem solving | Diffusion model | Consistency model | Fast sampling

7. Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems NSTL国家科技图书文献中心

Ziyuan Luo | Boxin Shi ... - 《Computer Vision - ECCV 2024,Part VII》 - European Conference on Computer Vision - 2025, - 350～368 - 共19页

摘要：Electromagnetic Inverse Scattering Problems | -resolution problems* arising from discretization. Further* | challenges posed by inverse* estimation. Our approach* | (EISP) have gained wide applications in computational | imaging. By solving EISP, the internal relative

关键词： Electromagnetic inverse scattering problems | Implicit neural representations | Computational photography

8. Single-Scan mpMRI Calibration of Multi-species Brain Tumor Dynamics with Mass Effect NSTL国家科技图书文献中心

Ali Ghafouri | George Biros - 《Simulation and Synthesis in Medical Imaging》 - International Workshop on Simulation and Synthesis in Medical Imaging | International Conference on Medical Image Computing and Computer Assisted Intervention - 2025, - 187～196 - 共10页

摘要： all three inverse* problems using quasi-Newton* | We propose an inverse* problem formulation and* | (mpMRI) scan. To solve this inverse* problem, we first* | the pretumor anatomy. Then we solve a second inverse | inverse problem. Finally, we solve a third inverse

关键词： Glioblastoma | Multi-species | Mass effect | Tumor growth models | Inverse problems

9. Robust Non-convex Model-Based Approach for Deep Learning-Based Image Processing NSTL国家科技图书文献中心

Elena Morotti | Davide Evangelista ... - 《Numerical Computations,Part I》 - International Conference on Numerical Computations: Theory and Algorithms - 2025, - 360～367 - 共8页

摘要：Total p-norm Variation (TpV) is a well | -established technique in image processing, used to denoise | and preserve edges. However, the related non-convex | minimization is still a challenging task in optimization | , both for the computational cost and for convergence

关键词： Non-convex optimization | Neural network | Inverse problems

10. Piecewise Linear Approximations in the Balanced Identification of Models with Differential Equations NSTL国家科技图书文献中心

Vladimir Voloshinov | Alexander Sokolov - 《Optimization and Applications》 - International Conference on Optimization and Applications - 2025, - 69～82 - 共14页

摘要： the technology generates inverse* problems for DE* | problems by finite dimensional mathematical programming | The work develops numerical methods of a | technology of balanced identification for mathematical | models with differential equations (DE). In this case

关键词： Balanced identification | Discretization of inverse problems | Discretization of differential equations | Piecewise linear approximations | Smoothing functions | SOS2 constraints

摘要：Recent studies on inverse problems have | range of inverse problems. However, the existing | Variational Inference (DAVI) that solves inverse problems | proposed posterior samplers that leverage the pre-trained | diffusion models as powerful priors. These attempts have

关键词： Inverse problems | Diffusion models | Posterior sampling

摘要：In imaging inverse problems, one seeks to | . Because such problems are ill-posed, there is great | recover an image from missing/corrupted measurements | motivation to quantify the uncertainty induced by the | measurement-and-recovery process. Motivated by applications

关键词： Inverse problems | Uncertainty quantification | Conformal prediction | Posterior sampling | MRI

摘要： generative techniques for solving inverse problems. Despite | their success in a variety of inverse problems in | , application of these ideas for solving inverse problems with | various noisy inverse problems, including Gaussian and | Diffusion models have emerged as powerful

关键词： Diffusion models | Zero-Shot learning | Inverse problems | Plug-and-Play (PnP) methods | Unrolled networks | Bayesian methods

摘要： inverse problems of wave tomography, namely, two | -coefficient inverse problems of reconstruction of unknown | This article explores the problems of | absorption in the inverse problem. Model calculations on a | convergence of iterative methods for solving nonlinear

关键词： Supercomputer simulations | High-performance scientific computing | Inverse problems | Ultrasound tomography | Nondestructive testing

摘要：Recent inverse problem solvers that leverage | seamless integration of 3D inverse solvers and thus leads | diffusion inverse solvers even when training with gold | generative diffusion priors have garnered significant | attention due to their exceptional quality. However

关键词： Diffusion models | Inverse problems | OOD adaptation

摘要： strong priors for solving general inverse problems | . Most existing Diffusion model-based Inverse Problem | achieves new state-of-the-art in diffusion-based inverse | employing prior-based inverse problem solvers for real | Diffusion models have been demonstrated as

关键词： Inverse problem solving | Diffusion model | Consistency model | Fast sampling

摘要：Electromagnetic Inverse Scattering Problems | -resolution problems arising from discretization. Further | challenges posed by inverse estimation. Our approach | (EISP) have gained wide applications in computational | imaging. By solving EISP, the internal relative

关键词： Electromagnetic inverse scattering problems | Implicit neural representations | Computational photography

摘要： all three inverse problems using quasi-Newton | We propose an inverse problem formulation and | (mpMRI) scan. To solve this inverse problem, we first | the pretumor anatomy. Then we solve a second inverse | inverse problem. Finally, we solve a third inverse

关键词： Glioblastoma | Multi-species | Mass effect | Tumor growth models | Inverse problems

摘要：Total p-norm Variation (TpV) is a well | -established technique in image processing, used to denoise | and preserve edges. However, the related non-convex | minimization is still a challenging task in optimization | , both for the computational cost and for convergence

关键词： Non-convex optimization | Neural network | Inverse problems

摘要： the technology generates inverse problems for DE | problems by finite dimensional mathematical programming | The work develops numerical methods of a | technology of balanced identification for mathematical | models with differential equations (DE). In this case

关键词： Balanced identification | Discretization of inverse problems | Discretization of differential equations | Piecewise linear approximations | Smoothing functions | SOS2 constraints

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：Recent studies on inverse* problems have* | range of inverse* problems. However, the existing* | Variational Inference (DAVI) that solves inverse problems | proposed posterior samplers that leverage the pre-trained | diffusion models as powerful priors. These attempts have

摘要：In imaging inverse* problems, one seeks to* | . Because such problems* are ill-posed, there is great* | recover an image from missing/corrupted measurements | motivation to quantify the uncertainty induced by the | measurement-and-recovery process. Motivated by applications

摘要： generative techniques for solving inverse* problems. Despite* | their success in a variety of inverse* problems in* | , application of these ideas for solving inverse* problems with* | various noisy inverse* problems, including Gaussian and* | Diffusion models have emerged as powerful

摘要： inverse problems of wave tomography, namely, two | -coefficient inverse* problems of reconstruction of unknown* | This article explores the problems* of* | absorption in the inverse* problem. Model calculations on a* | convergence of iterative methods for solving nonlinear

摘要：Recent inverse* problem solvers that leverage* | seamless integration of 3D inverse* solvers and thus leads* | diffusion inverse* solvers even when training with gold* | generative diffusion priors have garnered significant | attention due to their exceptional quality. However

摘要： strong priors for solving general inverse problems | . Most existing Diffusion model-based Inverse* Problem* | achieves new state-of-the-art in diffusion-based inverse | employing prior-based inverse* problem solvers for real* | Diffusion models have been demonstrated as

摘要：Electromagnetic Inverse Scattering Problems | -resolution problems* arising from discretization. Further* | challenges posed by inverse* estimation. Our approach* | (EISP) have gained wide applications in computational | imaging. By solving EISP, the internal relative

摘要： all three inverse* problems using quasi-Newton* | We propose an inverse* problem formulation and* | (mpMRI) scan. To solve this inverse* problem, we first* | the pretumor anatomy. Then we solve a second inverse | inverse problem. Finally, we solve a third inverse

摘要： the technology generates inverse* problems for DE* | problems by finite dimensional mathematical programming | The work develops numerical methods of a | technology of balanced identification for mathematical | models with differential equations (DE). In this case