English

AssetGen: Deployable 3D Asset Generation at Interactive Speed

Graphics 2026-05-27 v1 Artificial Intelligence Computer Vision and Pattern Recognition

Abstract

While 3D generation is progressing rapidly, recent work has often focused on obtaining high-resolution assets, leaving user experience and deployability as afterthoughts. We present AssetGen, a 3D generator that focuses instead on these two aspects. Given one reference image, in 30 seconds it produces a high-quality mesh with baked normals, a color texture, and a controlled polygon budget suitable for real-time rendering, including mobile use cases. The AssetGen Flash variant further reduces latency to 14 seconds for interactive and agentic creation loops. Our model generates the object geometry with a coarse-to-refine VecSet framework, which implements mesh simplification, cleaning, and normal baking on the GPU, and a fast parallel UV unwrapping. It then generates textures in a multi-view fashion, followed by backprojection and 3D inpainting. Model distillation, kernel optimization, and pipeline parallelization are co-designed to accelerate the system end-to-end. We introduce numerous automated and blind human evaluations and demonstrate competitive visual quality against leading commercial solutions in 30 seconds and preview-quality results in less than 15 seconds. The final result is a system that supports AI-assisted, deployable 3D content creation in interactive workflows.

Keywords

Cite

@article{arxiv.2605.26137,
  title  = {AssetGen: Deployable 3D Asset Generation at Interactive Speed},
  author = {Dilin Wang and Xiaoyu Xiang and Kihyuk Sohn and Tom Monnier and Yu-Ying Yeh and Thu Nguyen-Phuoc and Jiawen Zhang and Yuchen Fan and Antoine Toisoul and Hyunyoung Jung and Prithviraj Dhar and Michael Bunnell and Nikolaos Sarafianos and Chuhang Zou and Roman Shapovalov and Andrea Vedaldi and Rakesh Ranjan},
  journal= {arXiv preprint arXiv:2605.26137},
  year   = {2026}
}