Generative models · MLD-0999
Rectified flow
A generative transport approach that learns approximately straight trajectories between paired source and target samples.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Reduce the complexity of generative sampling trajectories.
Original caveat
Straight training paths do not guarantee exact one-step sampling.
Context and aliases
Level: Advanced. Stages: Architecture · Training · Inference.
Tags: DL · Generative AI · Vision.
Aliases: None recorded.
Related concepts
Original references
- Denoising Diffusion Probabilistic Models ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- Flow Matching for Generative Modeling ↗ · Consulted
- Auto-Encoding Variational Bayes ↗ · Consulted
- Original reference URL ↗