paper-with-me

Papers

CAFLOW: Conditional Autoregressive Flows

2021-06-04 · Georgios Batzolis, Marcello Carioni, Christian Etmann, Soroosh Afyouni, Zoe Kourtzi, Carola Bibiane Schönlieb

We introduce CAFLOW, a new diverse image-to-image translation model that simultaneously leverages the power of auto-regressive modeling and the modeling efficiency of conditional normalizing flows. We transform the conditioning image into a sequence of latent encodings using a multi-scale normalizing flow and repeat the process for the conditioned image. We model the conditional distribution of the latent encodings by modeling the auto-regressive distributions with an efficient multi-scale normalizing flow, where each conditioning factor affects image synthesis at its respective resolution scale. Our proposed framework performs well on a range of image-to-image translation tasks. It outperforms former designs of conditional flows because of its expressive auto-regressive structure.

📄 PDF Abstract BibTeX arXiv:2106.02531

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationImage-to-Image TranslationTranslation

Similar Papers 제목 키워드 기반

DeCaFlow: A Deconfounding Causal Generative Model

2025-03-19 · Alejandro Almodóvar, Adrián Javaloy, Juan Parras, Santiago Zazo 외

We introduce DeCaFlow, a deconfounding causal generative model. Training once per dataset using just observational data and the underlying causal graph, DeCaFlow enables accurate causal inference on continuous variables …

Causal Inferencecounterfactualmodel

CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow

2025-11-26 · Ruisheng Han, Kanglei Zhou, Shuang Chen, Amir Atapour-Abarghouei 외 arxiv

Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics,…

Action Quality Assessment

Neural Autoregressive Flows

2018-04-03 · ICML 2018 7 · Chin-wei Huang, David Krueger, Alexandre Lacoste, Aaron Courville

Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-bas…

Density EstimationSpeech Synthesis

Autoregressive Quantile Flows for Predictive Uncertainty Estimation

2021-12-09 · ICLR 2022 4 · Phillip Si, Allan Bishop, Volodymyr Kuleshov

Numerous applications of machine learning involve representing probability distributions over high-dimensional data. We propose autoregressive quantile flows, a flexible class of normalizing flow models trained using a n…

Density Estimationobject-detectionObject Detectionregression+3

Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics

2021-04-09 · Mohsen Zand, Ali Etemad, Michael Greenspan

Conditional Normalizing Flows (CNFs) are flexible generative models capable of representing complicated distributions with high dimensionality and large interdimensional correlations, making them appealing for structured…

motion predictionPredictionStructured PredictionTime Series+3