AssetGen: Deployable 3D Asset Generation at Interactive Speed

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Dilin, Xiang, Xiaoyu, Sohn, Kihyuk, Monnier, Tom, Yeh, Yu-Ying, Nguyen-Phuoc, Thu, Zhang, Jiawen, Fan, Yuchen, Toisoul, Antoine, Jung, Hyunyoung, Dhar, Prithviraj, Bunnell, Michael, Sarafianos, Nikolaos, Zou, Chuhang, Shapovalov, Roman, Vedaldi, Andrea, Ranjan, Rakesh
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917532939583488
author Wang, Dilin
Xiang, Xiaoyu
Sohn, Kihyuk
Monnier, Tom
Yeh, Yu-Ying
Nguyen-Phuoc, Thu
Zhang, Jiawen
Fan, Yuchen
Toisoul, Antoine
Jung, Hyunyoung
Dhar, Prithviraj
Bunnell, Michael
Sarafianos, Nikolaos
Zou, Chuhang
Shapovalov, Roman
Vedaldi, Andrea
Ranjan, Rakesh
author_facet Wang, Dilin
Xiang, Xiaoyu
Sohn, Kihyuk
Monnier, Tom
Yeh, Yu-Ying
Nguyen-Phuoc, Thu
Zhang, Jiawen
Fan, Yuchen
Toisoul, Antoine
Jung, Hyunyoung
Dhar, Prithviraj
Bunnell, Michael
Sarafianos, Nikolaos
Zou, Chuhang
Shapovalov, Roman
Vedaldi, Andrea
Ranjan, Rakesh
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26137
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AssetGen: Deployable 3D Asset Generation at Interactive Speed
Wang, Dilin
Xiang, Xiaoyu
Sohn, Kihyuk
Monnier, Tom
Yeh, Yu-Ying
Nguyen-Phuoc, Thu
Zhang, Jiawen
Fan, Yuchen
Toisoul, Antoine
Jung, Hyunyoung
Dhar, Prithviraj
Bunnell, Michael
Sarafianos, Nikolaos
Zou, Chuhang
Shapovalov, Roman
Vedaldi, Andrea
Ranjan, Rakesh
Graphics
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title AssetGen: Deployable 3D Asset Generation at Interactive Speed
topic Graphics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.26137