cs.CVOct 30, 2026

VoxLution: Evolving Voxels for High-Fidelity 3D Scene Generation

Authors: Daoyi Gao, Xinyi Zhang, Alexey Bokhovkin, Lei Li, Angela Dai

Organizations: Technical University of Munich · University of Virginia

Abstract

High-resolution 3D indoor scene generation is crucial for immersive applications such as virtual reality, spatial computing, and robotics simulation. We introduce VoxLution, a coarse-to-fine transformer-based approach that generates high-fidelity indoor scenes with rich details, overcoming the overly smooth geometry typical of existing generative models. First, we generate a low-resolution spatial layout; then, based on this structural information, we progressively refine the scene geometry locally in chunks. Key to our approach is formulating 3D super-resolution as a sequence modeling problem over multi-resolution sparse voxel grids. To achieve this, we introduce a training-free, resolution-invariant tokenization scheme that compactly encodes the geometric information of eight octants into a single decimal number. We formulate the transformer sequence to include multiple resolutions, allowing the coarse layout to guide the generation of fine local details. To ensure coherence across local chunks, we incorporate adjacent chunk boundary information directly into the transformer sequencing. VoxLution achieves scene generation at a finer voxel resolution than existing baselines, demonstrating state-of-the-art performance on standard benchmarks with 59.6% lower FPD and 51.1% lower FID on 3D-FRONT, and 70.5% lower FPD and 73.8% lower FID on Scannet++.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation

    Jul 15, 2026Bin Zang, Wenting Zheng, Xiaoliang Luo +83D Scene Generation3D Scene Representation

  2. ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning

    Jul 15, 2026Yuan Xiao, Can Wang, Xiangyu Kong +13D Scene Editing3D Scene Generation

  3. Sparse auto-regressive modeling for scene generation from multi-view images

    Sep 3, 2026Thomas Lucas, Maxime Pietrantoni, Philippe Weinzaepfel +4Sparse-View 3D Reconstruction3D Scene Generation