JoVox-64

Image-conditioned 64³ voxel structure generator of JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation. JoVox is a discrete flow matching framework that learns the joint hierarchical distribution of voxels while keeping generation lightweight. One model generates all levels, 4³ → 16³ → 64³, from a single image.

Paper: arXiv:2611.10690 · Code: github.com/yuyujunjun/JoVox

Usage

Install the code as described in its README, then download the weights:

hf download xiangjuntang/JoVox-64 model.safetensors --local-dir checkpoints/voxelgen64

Generate a structure and a mesh from your own images:

python scripts/img2mesh.py --stage prep  --in_dir <images> --out <out>   # TRELLIS.2 environment
python scripts/img2mesh.py --stage voxel --out <out> --seed 0             # JoVox environment
python scripts/img2mesh.py --stage mesh  --out <out> --seed 0             # TRELLIS.2 environment

Model

The condition image is encoded by DINOv3, which is downloaded separately.

Training Data

The sketchfab, 3D-FUTURE, HSSD and ABO subsets of TRELLIS-500K. Toys4k was held out for testing.

Results

On 1000 Toys4k objects (image-conditioned), compared with TRELLIS.2 with the same backbone:

Citation

@article{tang2026jovox,
    title   = {JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation},
    author  = {Tang, Xiangjun and Chen, Jianqi and Wonka, Peter},
    journal = {arXiv preprint arXiv:2611.10690},
    year    = {2026}
}