Awesome Computed Tomography EN 在 GitHub 上加星标

隐式神经表示

隐式神经表示(INR)是指把待求的 CT 体数据表示为一个坐标网络,把三维(或三维加时间)位置映射为衰减值,并拟合该网络,使其模拟投影与实测投影一致。网络本身就是图像;重建是逐扫描的优化,而不是用预训练模型做推理。

由于表示是连续的、针对每次扫描拟合,INR 不需要训练数据,能自然地处理稀疏视角、有限角和动态采集;多分辨率哈希编码使其速度足以处理锥束体数据。这一类方法常被称为神经衰减场或 NeRF 式 X 射线方法。

当前工作集中在:减少过度平滑或拟合噪声的编码与网络结构、来自预训练模型或扩散模型的先验、用于 4D-CT 的运动场、用于金属伪影的多色前向模型,以及不确定性量化。高斯溅射是与之密切相关的显式替代方案,有单独的主题页。

在可检索的目录中浏览全部 25 篇「隐式神经表示」论文

入门推荐

如果你刚接触这个主题,可以先读这几篇;由维护者挑选。

论文

全部 25 篇,按时间倒序。

论文发表出处年份链接
DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic ReconstructionAAAI2026paper · project
Regularizing INR with Diffusion Prior for Self-Supervised 3D Reconstruction of Neutron Computed Tomography DataICASSP2026paper
Dynamic Black-hole Emission Tomography with Physics-Informed Neural FieldsCVPR2026paper
Field-of-View Extension in Dental Cone-Beam CT via Implicit Neural Representations and Diffusion Model-Based RefinementMICAD2026paper · code
GH-NAF: Grid-Adaptive Hash-Level-Attended Neural Attenuation Fields for Discrepancy-Aware CBCTCVPR2026paper · code
NAB: Neural Adaptive Binning for Sparse-View CT ReconstructionICLR2026paper · code
OX-NeRF: 3D X-ray Tomography Reconstruction from Sparse Views Using Implicit Neural Representation预印本2026paper
Texture-preserving implicit neural representation for cone-beam CT truncated reconstruction预印本2026paper
Accelerated Optimization of Implicit Neural Representations for CT ReconstructionISBI2025paper
Coordinate-Based Speed of Sound Recovery for Aberration-Corrected Photoacoustic Computed TomographyICCV2025paper · project
Iterative Diffusion-Refined Neural Attenuation Fields for Multi-Source Stationary TomographyTCI2025paper
Epi-NAF: Enhancing Neural Attenuation Fields for Limited-Angle CT with Epipolar ConsistencyISBI2025paper
Nonperiodic dynamic CT reconstruction using backward-warping INR with regularization of diffeomorphism (BIRD)预印本2025paper
Recover Biological Structure from Sparse-View Diffraction Images with Neural Volumetric PriorICCV2025paper
Unsupervised Self-Prior Embedding Neural Representation for Sparse-View CT ReconstructionAAAI2025paper · code
INCODE: Implicit Neural Conditioning with Prior Knowledge EmbeddingsWACV2024paper · code
Implicit Neural Representations for Robust Joint Sparse-View CT ReconstructionTMLR2024paper · code
Neural Field Regularization by Denoising for 3D Sparse-View X-Ray Computed Tomography3DV2024paper
Structure-Aware Sparse-View X-Ray 3D ReconstructionCVPR2024paper · code
PINER: Prior-Informed Implicit Neural Representation Learning for Test-Time Adaptation in Sparse-View CT ReconstructionWACV2023paper · code
Unsupervised Polychromatic Neural Representation for CT Metal Artifact ReductionNeurIPS2023paper · code
UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed TomographyTMLR2023paper
NAF: Neural Attenuation Fields for Sparse-View CBCT ReconstructionMICCAI2022paper · code
SNAF: Sparse-View CBCT Reconstruction with Neural Attenuation Fields预印本2022paper
Dynamic CT Reconstruction From Limited Views With Implicit Neural RepresentationsICCV2021paper

在可检索的目录中浏览全部 25 篇「隐式神经表示」论文

数据集、基准与工具库

目录中任务或标签与本主题相符的条目。

指南

涵盖本主题的指南。

其他主题