Generative Tomography Reconstruction

• URL: http://arxiv.org/abs/2010.14933v2
• Date: Wed, 25 Nov 2020 22:05:56 GMT
• Title: Generative Tomography Reconstruction
• Authors: Matteo Ronchetti, Davide Bacciu
• Abstract summary: We propose an end-to-end differentiable architecture for tomography reconstruction that maps a noisy sinogram into a denoised reconstruction. We also propose a generative model that, given a noisy sinogram, can sample realistic reconstructions.
• Score: 11.460692362624533
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose an end-to-end differentiable architecture for tomography reconstruction that directly maps a noisy sinogram into a denoised reconstruction. Compared to existing approaches our end-to-end architecture produces more accurate reconstructions while using less parameters and time. We also propose a generative model that, given a noisy sinogram, can sample realistic reconstructions. This generative model can be used as prior inside an iterative process that, by taking into consideration the physical model, can reduce artifacts and errors in the reconstructions.

Related papers

• Likelihood-Scheduled Score-Based Generative Modeling for Fully 3D PET Image Reconstruction [40.34650079545031]
  We propose a practical methodology for fully 3D reconstruction that accelerates reconstruction and reduces the number of critical hyper parameters. We show our methodology can match or improve on the NRMSE and SSIM of existing state-of-the-art SGM-based PET reconstruction. We demonstrate a first-ever implementation of SGM-based reconstruction for real 3D PET data, specifically $[18$F]DPA-714 data.
  arXiv  Detail & Related papers  (2024-12-05T16:58:45Z)
• ReMatching Dynamic Reconstruction Flow [55.272357926111454]
  We introduce the ReMatching framework, designed to improve generalization quality by incorporating deformation priors into dynamic reconstruction models. The framework is highly adaptable and can be applied to various dynamic representations. Our evaluations on popular benchmarks involving both synthetic and real-world dynamic scenes demonstrate a clear improvement in reconstruction accuracy of current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-11-01T16:09:33Z)
• Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization [18.24882084542254]
  We present an array of reconstruction techniques that can significantly reduce this error by more than $90%$. We find out that a strategy of self-generating calibration data can mitigate this trade-off between reconstruction and generalization.
  arXiv  Detail & Related papers  (2024-06-21T05:13:34Z)
• SMORE: Simulataneous Map and Object REconstruction [66.66729715211642]
  We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly-moving objects and the background.
  arXiv  Detail & Related papers  (2024-06-19T23:53:31Z)
• Model-corrected learned primal-dual models for fast limited-view photoacoustic tomography [2.631277214890658]
  Learned iterative reconstructions hold promise to accelerate tomographic imaging with empirical robustness to model perturbations. Computational feasibility can be obtained by the use of fast approximate models, but a need to compensate model errors arises. We advance the methodological and theoretical basis for model corrections in learned image reconstructions by embedding the model correction in a learned primal-dual framework.
  arXiv  Detail & Related papers  (2023-04-04T17:13:22Z)
• DiffusER: Discrete Diffusion via Edit-based Reconstruction [88.62707047517914]
  DiffusER is an edit-based generative model for text based on denoising diffusion models. It can rival autoregressive models on several tasks spanning machine translation, summarization, and style transfer. It can also perform other varieties of generation that standard autoregressive models are not well-suited for.
  arXiv  Detail & Related papers  (2022-10-30T16:55:23Z)
• Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes [52.038346313823524]
  This paper introduces a novel framework called DTNet for 3D mesh reconstruction and generation via Disentangled Topology. Our method is able to produce high-quality meshes, particularly with diverse topologies, as compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-06-10T08:32:57Z)
• Towards performant and reliable undersampled MR reconstruction via diffusion model sampling [67.73698021297022]
  DiffuseRecon is a novel diffusion model-based MR reconstruction method. It guides the generation process based on the observed signals. It does not require additional training on specific acceleration factors.
  arXiv  Detail & Related papers  (2022-03-08T02:25:38Z)
• Structured Outdoor Architecture Reconstruction by Exploration and Classification [34.066110654930476]
  We present an explore-and-classify framework for structured architectural reconstruction from an aerial image. We learn to classify the correctness of building models while generating classification labels based on the ground-truth. We evaluate the approach using initial reconstructions by two baselines and two state-of-the-art reconstruction algorithms.
  arXiv  Detail & Related papers  (2021-08-18T06:28:26Z)
• Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases [131.50372468579067]
  We represent the reconstructed surface as an atlas, using a neural network. We empirically show that our method achieves results that exceed that state of the art in the accuracy of unsupervised correspondences and accuracy of surface reconstruction.
  arXiv  Detail & Related papers  (2021-04-14T16:21:22Z)
• Limited View Tomographic Reconstruction Using a Deep Recurrent Framework with Residual Dense Spatial-Channel Attention Network and Sinogram Consistency [25.16002539710169]
  We propose a novel recurrent reconstruction framework that stacks the same block multiple times. We develop a sinogram consistency layer interleaved in our recurrent framework to ensure that the sampled sinogram is consistent with the sinogram of the intermediate outputs of the recurrent blocks. Our algorithm achieves a consistent and significant improvement over the existing state-of-the-art neural methods on both limited angle reconstruction and sparse view reconstruction.
  arXiv  Detail & Related papers  (2020-09-03T16:39:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.