Improving Rectified Flow with Boundary Conditions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908601169215488 |
|---|---|
| author | Hu, Xixi Liao, Runlong Xu, Keyang Liu, Bo Li, Yeqing Ie, Eugene Fei, Hongliang Liu, Qiang |
| author_facet | Hu, Xixi Liao, Runlong Xu, Keyang Liu, Bo Li, Yeqing Ie, Eugene Fei, Hongliang Liu, Qiang |
| contents | Rectified Flow offers a simple and effective approach to high-quality generative modeling by learning a velocity field. However, we identify a limitation in directly modeling the velocity with an unconstrained neural network: the learned velocity often fails to satisfy certain boundary conditions, leading to inaccurate velocity field estimations that deviate from the desired ODE. This issue is particularly critical during stochastic sampling at inference, as the score function's errors are amplified near the boundary. To mitigate this, we propose a Boundary-enforced Rectified Flow Model (Boundary RF Model), in which we enforce boundary conditions with a minimal code modification. Boundary RF Model improves performance over vanilla RF model, demonstrating 8.01% improvement in FID score on ImageNet using ODE sampling and 8.98% improvement using SDE sampling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_15864 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Rectified Flow with Boundary Conditions Hu, Xixi Liao, Runlong Xu, Keyang Liu, Bo Li, Yeqing Ie, Eugene Fei, Hongliang Liu, Qiang Machine Learning Rectified Flow offers a simple and effective approach to high-quality generative modeling by learning a velocity field. However, we identify a limitation in directly modeling the velocity with an unconstrained neural network: the learned velocity often fails to satisfy certain boundary conditions, leading to inaccurate velocity field estimations that deviate from the desired ODE. This issue is particularly critical during stochastic sampling at inference, as the score function's errors are amplified near the boundary. To mitigate this, we propose a Boundary-enforced Rectified Flow Model (Boundary RF Model), in which we enforce boundary conditions with a minimal code modification. Boundary RF Model improves performance over vanilla RF model, demonstrating 8.01% improvement in FID score on ImageNet using ODE sampling and 8.98% improvement using SDE sampling. |
| title | Improving Rectified Flow with Boundary Conditions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.15864 |