AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Improving Rectified Flow with Boundary Conditions

Xixi Hu, Runlong Liao, Keyang Xu, Bo Liu, Yeqing Li, Eugene Ie, Hongliang Fei, Qiang Liu

ICCV 2025 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
enforce both t=0 and t=1 boundary conditions via mask-based parameterization (ablation)Rectified Flow DiT-B/2 · ImageNet 256x256 (SDE)FID: 6.79 -> 6.18Improved
enforce only the right boundary (t=1) with a single pass (ablation)Rectified Flow DiT-B/2 · ImageNet 256x256 (Euler)FID: 6.87 -> 6.80Improved
right-boundary-only enforcement lowers IS (ablation)Rectified Flow DiT-B/2 · ImageNet 256x256 (Euler)IS: 130.08 -> 125.44Hurt
use subtraction-based parameterization (extra forward pass at t=1) (ablation)Rectified Flow DiT-B/2 · ImageNet 256x256 (Euler)FID: 6.87 -> 6.32Improved
boundary enforcement versus mode sampling of timesteps near boundariesRectified Flow DiT-B/2 · ImageNet 256x256 (Euler)FID: 7.48 -> 6.32Improved
add classifier-free guidance with SDE samplerSubtraction-based Boundary RF · ImageNet 256x256 with CFG (SDE)FID: 7.20 -> 6.94 vs vanilla; but CFG SDE worse than no-CFG 6.38Mixed
use cosine boundary functions instead of offset cosine, quadratic, sqrt, or linear (ablation)Mask-based Boundary RF · ImageNet 256x256FID and ISImproved
enforce boundary conditions under stronger stochasticity (overshooting sampler noise scale c=5)Mask-based Boundary RF · ImageNet 256 overshooting sampler c=5FID: 11.76 -> 10.68Improved
scale boundary RF to larger models and DiT-L SDE samplerMask-based Boundary RF · ImageNet 256x256 (SDE) DiT-LFID: 6.77 -> 4.86Improved
mask-based boundary on DiT-L with Euler samplerMask-based Boundary RF · ImageNet 256x256 (Euler) DiT-LIS: 165.44 -> 162.34Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy