Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
Chin-wei Huang, Laurent Dinh, Aaron Courville
2020-02-17Image Generation
Abstract
In this work, we propose a new family of generative flows on an augmented data space, with an aim to improve expressivity without drastically increasing the computational cost of sampling and evaluation of a lower bound on the likelihood. Theoretically, we prove the proposed flow can approximate a Hamiltonian ODE as a universal transport map. Empirically, we demonstrate state-of-the-art performance on standard benchmarks of flow-based generative modeling.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Image Generation | ImageNet 32x32 | bpd | 3.92 | ANF Huang et al. (2020) |
| Image Generation | CelebA 256x256 | bpd | 0.72 | ANF Huang et al. (2020) |
Related Papers
fastWDM3D: Fast and Accurate 3D Healthy Tissue Inpainting2025-07-17Synthesizing Reality: Leveraging the Generative AI-Powered Platform Midjourney for Construction Worker Detection2025-07-17FashionPose: Text to Pose to Relight Image Generation for Personalized Fashion Visualization2025-07-17A Distributed Generative AI Approach for Heterogeneous Multi-Domain Environments under Data Sharing constraints2025-07-17Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical Images2025-07-17FADE: Adversarial Concept Erasure in Flow Models2025-07-16CharaConsist: Fine-Grained Consistent Character Generation2025-07-15CATVis: Context-Aware Thought Visualization2025-07-15