cs.CVNov 16, 2026

Multi-Rate Flow Matching for Point Cloud Upsampling

Authors: Jingkai Shang, Edgar Torres, Duy Nguyen

Organizations: Institute for Artificial Intelligence, University of Stuttgart, Stuttgart, Germany

Abstract

Flow-matching point-cloud upsamplers refine sparse inputs into dense point clouds by integrating a learned velocity field with a fixed temporal discretization. However, local reconstruction requirements vary substantially across a shape, while a shared solver budget applies the same temporal resolution everywhere. We propose Multi-Rate Flow Matching (MRFM), a patch-adaptive framework that selects an integration budget for each local patch at inference time while keeping the learned velocity field frozen. MRFM relaxes the discrete budget into a continuous variable, optimizes it online through differentiable soft rollouts using an input-derived geometric fidelity objective, and projects the result back to a discrete budget for the final solver rollout. Experiments on PU1K and PUGAN show strong reconstruction quality, while matched-budget permutation and multi-factor analyses demonstrate that the benefit depends on patch-specific allocation rather than on the step distribution alone. MRFM is accuracy-oriented and intentionally uses additional test-time optimization to obtain more suitable local temporal resolutions.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud Upsampling

    Oct 15, 2026Yuang Liu, Zhi Zuo, Zhengkai Zhao +4Point Cloud LearningFlow Matching

  2. Hierarchical Flow Matching for 3D Point Cloud Generation

    Aug 6, 2026Linhao Wang, Qichang Zhang, Ye Su +1Flow Matching3D Shape Generation

  3. Point Cloud Upsampling through Patch-based Frequency Superposition

    Jun 12, 2026Marina Ritthaler, Azhar Hussian, Vasileios Belagiannis +13D ReconstructionPoint Cloud Learning