normalizing-flow

Trustworthy Image Super-Resolution via Generative Pseudoinverse [ICLR 2025 DeLTa Workshop]

Normalizing-flow generation of realistic synthetic clinical outcomes

Modern normalizing flows in Python. Simple to use and easily extensible.

Evidence-Based Multi-Method Feature Engineering Pipeline for Unsupervised Industrial Audio Anomaly Detection.

The official implementation of smooth prototype equivalences (SPE), used to classify and characterize observations from empirical vector field data.

Code for the paper "Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations" (ICML 2024)

(Conditional) Normalizing Flows in PyTorch. Offers a wide range of (conditional) invertible neural networks.

Reduce a large and high-dimensional dataset by downselecting data uniformly in phase space

Reproduction of Normalizing Flow with PyTorch

Coursework and projects for Deep Generative Models(DGM) course(Graduate), including theoretical homework solutions/problems, final solution/problems and the project of the course

A Julia framework for invertible neural networks

Training a normalizing flow (NF) to generate samples from a multi-dimensional distribution

This repo implements normalizing flow model with a simple realnvp like model and provides training and sampling code on mnist dataset

A BNAF implementation in Flax

Expert knowledge elicitation method for learning prior distribution in Bayesian models based on expert knowledge.

📖 The official code repository for the second edition of the O'Reilly book Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play.

Official implementation of GLARE, which is accpeted by ECCV 2024.

This repository contains the code, data and report for a coursework project that mainly focuses on learning and sampling complex distributions using normalizing flows

This repository implements REAL NVP (Real-valued Non-Volume Preserving), a normalizing flow model that uses coupling layers to transform complex data into a simpler distribution, like a Gaussian. It efficiently reconstructs realistic data from a normal distribution without iterative steps, making inference fast.

Official code base of "Perception-Oriented Video Frame Interpolation via Asymmetric Blending" (CVPR 2024), also denoted as ''PerVFI''.