Representing a signal as a continuous function parameterized by neural network (a.k.a. Implicit Neural Representations, INRs) has attracted increasing attention in recent years. Neural Processes (NPs), which model the distributions over functions conditioned on partial observations (context set), provide a practical solution for fast inference of continuous functions. However, existing NP architectures suffer from inferior modeling capability for complex signals. In this paper, we propose an efficient NP framework dubbed Versatile Neural Processes (VNP), which largely increases the capability of approximating functions. Specifically, we introduce a bottleneck encoder that produces fewer and informative context tokens, relieving the high computational cost while providing high modeling capability. At the decoder side, we hierarchically learn multiple global latent variables that jointly model the global structure and the uncertainty of a function, enabling our model to capture the distribution of complex signals. We demonstrate the effectiveness of the proposed VNP on a variety of tasks involving 1D, 2D and 3D signals. Particularly, our method shows promise in learning accurate INRs w.r.t. a 3D scene without further finetuning. Code is available at https://github.com/ZongyuGuo/Versatile-NP .
Correcting Model Bias with Sparse Implicit Processes
Institute of Mathematical Sciences (ICMAT-CSIC)(数学科学研究所(ICMAT-CSIC));Escuela Politécnica Superior, Universidad Autónoma de Madrid(马德里自治大学高等理工学院);Institute of Corpuscular Physics, University of Valencia and CSIC(瓦伦西亚大学与西班牙国家研究委员会粒子物理研究所)
Function-space Inference with Sparse Implicit Processes
Institute of Mathematical Sciences (ICMAT-CSIC)(数学科学研究所(ICMAT-CSIC));Institute of Corpuscular Physics, University of Valencia and CSIC(瓦伦西亚大学与西班牙国家研究委员会微粒物理研究所);Escuela Politécnica Superior, Universidad Autónoma de Madrid(马德里自治大学高等理工学院)
PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRI
Helmholtz Munich(亥姆霍兹慕尼黑中心);Technical University of Munich(慕尼黑工业大学);Klinikum rechts der Isar(右岸医院(慕尼黑工业大学附属));Imperial College London(帝国理工学院);Pontificia Universidad Católica de Chile(智利天主教大学);King’s College London(伦敦国王学院)
Physics-Guided Dual Implicit Neural Representations for Source Separation
Linac Coherent Light Source, SLAC National Accelerator Laboratory(直线相干光源,SLAC国家加速器实验室);Stanford Institute for Materials and Energy Sciences(斯坦福材料与能源科学研究所);Stanford University(斯坦福大学);SLAC National Accelerator Laboratory(SLAC国家加速器实验室);Computer Science and Engineering Department(计算机科学与工程系);University of California Santa Cruz(加州大学圣克鲁兹分校);Neutron Scattering Division, Oak Ridge National Laboratory(中子散射部,橡树岭国家实验室);Department of Physics and Astronomy(物理与天文学系);Howard University(霍华德大学);Physics Department(物理系);Northeastern University(东北大学)