AssetGen: Deployable 3D Asset Generation at Interactive Speed
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 91 of its 106 references that are in the map. First posted on arXiv 22 May 2026.
Builds on
91 of 106 references.
References · 91
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2022Scalable Diffusion Models with Transformerscited by 5,931
- 2022Classifier-Free Diffusion Guidancecited by 5,717
- 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
- 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
- 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
38 more
- 2023Consistency Modelscited by 1,778
- 2020GLU Variants Improve Transformercited by 1,724
- 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
- 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
- 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
- 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
- 2023One-step Diffusion with Distribution Matching Distillationcited by 978
- 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
- 2023Vision Transformers Need Registerscited by 844
- 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
- 2025SAM 3: Segment Anything with Conceptscited by 835
- 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
- 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
- 2023Adversarial Diffusion Distillationcited by 741
- 2022On Distillation of Guided Diffusion Modelscited by 721
- 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
- 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
- 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
- 2024FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisioncited by 507
- 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 498
- 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
- 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
- 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
- 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
- 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
- 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
- 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
- 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
- 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
- 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 303
- 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
- 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
- 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
- 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
- 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214
- 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
- 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
- 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
50 most cited of 91 All 91 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
- 2026Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
- 2025MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation
- 2024Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning
- 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
- 2025Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
- 2026Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design
- 2024Edify 3D: Scalable High-Quality 3D Asset Generation