cs.CVNov 7, 2026

JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation

Authors: Xiangjun Tang, Jianqi Chen, Peter Wonka

Organizations: King Abdullah University of Science and Technology (KAUST)

Abstract

Generating high-fidelity voxels while keeping their lightweight nature remains an open problem in computer vision. Current generators are either high-fidelity but computationally heavy, or lightweight but of lower fidelity. Hierarchical methods keep the lightweight nature of voxels. However, their coarse levels, which decide where all finer cells can appear, are generated with the least information about the shape and are never revisited, so they are often plausible but wrong. Our key insight is to let finer cells take part in deciding coarse cells. To this end, we propose JoVox, a discrete flow matching framework that learns the joint distribution of all levels of the voxel hierarchy, instead of a separate distribution for each level, so that coarse cells can be predicted with finer cells already generated nearby. Within this framework, we further introduce a two-level prediction, which outputs the cells two levels finer at once instead of one level finer, halving the number of levels that the network processes and yielding voxels of higher fidelity. We also introduce an unmasking strategy that revisits early decisions once finer cells are generated and corrects inconsistencies in masked diffusion models. Our framework outperforms the baselines on both unconditional and image-conditioned voxel generation. Compared with the current state-of-the-art TRELLIS.2, we achieve 8x higher training throughput, 1/15 of the FLOPs in a forward pass, train on 4 vs. 32 GPUs, and obtain higher quality with an 11% lower Chamfer distance.

Figures & tables

Explore similar work

CardsList
  1. DVD: Discrete Voxel Diffusion for 3D Generation and Editing

    May 8, 2026Zhengrui Xiang, Jiaqi Wu, Fupeng Sun +23D Shape Editing3D Shape Generation

  2. Perceptual Flow Matching for Few-Step Generative Modeling

    Jul 3, 2026Chuyang Zhao, Yifei Song, Hongfa Wang +7Flow MatchingPerceptual Loss

  3. LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents

    Mar 6, 2026Tianhao Zhao, Youjia Zhang, Hang Long +73D Mesh Generation3D Representation Learning