cs.CVNov 19, 2026

One-to-Many: Diverse and Bidirectional Image-to-Image Translation via Rectified Flow

Authors: Sho Shimotsumagari, Seiichi Uchida, Shumpei Takezaki

Organizations: Kyushu University, Fukuoka, Japan · Current affiliation: CyberAgent, Inc.

Abstract

Many paired image-to-image translation tasks admit multiple valid target appearances, while training provides only one target per source. We propose One-to-Many Flow (O2MFlow), a latent-conditioned Rectified Flow (RF) model for one-to-many generation and backward translation (target→\rightarrowsource) within a single transport framework. Conditioning the RF dynamics on an appearance latent turns transport into a family of latent-indexed bijections: a fixed latent gives a mapping that is inverted by time-reversed integration, and sampled latents produce diverse outputs for the same input. We formalize reusable appearance variations as Shared Latent Transport and show that Kullback--Leibler (KL) regularization directly controls the source--latent distribution gap between training and generation. Across three benchmarks, O2MFlow offers dataset-dependent forward diversity--fidelity trade-offs and the lowest backward LPIPS-Dist among evaluated methods, with the lowest backward FID on two benchmarks.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. UniCycleFlow: Bidirectional Unpaired Image Translation with a Shared Rectified Flow

    Aug 7, 2026Xianhao Zhou, Jianghao Wu, Shaoting Zhang +1Image-to-Image TranslationRectified Flow

  2. Improving Image-to-Image Translation via a Rectified Flow Reformulation

    Mar 20, 2026Satoshi Iizuka, Shun Okamoto, Kazuhiro FukuiImage-to-Image TranslationRectified Flow

  3. FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing

    Nov 3, 2026Zhixian Li, Xingsong Ye, Yongkun Du +6Flow-Based Image EditingImage Text Translation