cs.LGMay 26, 2025

Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning

Authors: Ziyi Zhang, Li Shen, Deheng Ye, Yong Luo, Huangxuan Zhao, Meng Liu, Wei Yu, Lefei Zhang

Organizations: School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University · School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University · Tencent Inc. · Xiaomi Inc., China

Abstract

Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation quality, such as per-view fidelity and cross-view consistency. Reinforcement learning (RL) finetuning offers a potential solution, yet existing approaches designed for single-image diffusion do not readily extend to the few-step T2MV setting, as they neglect cross-view coordination and suffer from weak learning signals in few-step regimes. To address this, we propose MVC-ZigAL, a tailored RL finetuning framework for few-step T2MV diffusion models. Specifically, its core insights are: (1) a new MDP formulation that jointly models all generated views and assesses their collective quality via a joint-view reward; (2) a novel advantage learning strategy that exploits the performance gains of a self-refinement sampling scheme over standard sampling, yielding stronger learning signals for effective RL finetuning; and (3) a unified RL framework that extends advantage learning with a Lagrangian dual formulation for multiview-constrained optimization, balancing single-view and joint-view objectives through adaptive primal-dual updates under a self-paced threshold curriculum that harmonizes exploration and constraint enforcement. Collectively, these designs enable robust and balanced RL finetuning for few-step T2MV diffusion models, yielding substantial gains in both per-view fidelity and cross-view consistency. Code is available at https://github.com/ZiyiZhang27/MVC-ZigAL.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward

    Mar 8, 2026Yihong Luo, Tianyang Hu, Weijian Luo +1RL for Diffusion ModelsReinforcement Learning

  2. Self-Consistency Geometry Injection for Multi-view Consistent Image Generation

    Oct 28, 2026Yupeng Xiao, Yankai Wu, Jianjie Luo +3Multi-View Image SynthesisMulti-View Consistency

  3. MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

    Jul 6, 2026Gal Fiebelman, Hadar Averbuch-Elor, Sagie BenaimMulti-View ConsistencyVideo Diffusion Models