mlsanityData to 7 Oct 2026

AssetGen: Deployable 3D Asset Generation at Interactive Speed

arXiv 2605.26137 ↗First posted 22 May 2026cs.GR cs.AI cs.CVcited by 2

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

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2022Classifier-Free Diffusion Guidancecited by 5,717
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  10. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  11. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  12. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
38 more
  1. 2023Consistency Modelscited by 1,778
  2. 2020GLU Variants Improve Transformercited by 1,724
  3. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  4. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  5. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  6. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  7. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  8. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  9. 2023Vision Transformers Need Registerscited by 844
  10. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  11. 2025SAM 3: Segment Anything with Conceptscited by 835
  12. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  13. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  14. 2023Adversarial Diffusion Distillationcited by 741
  15. 2022On Distillation of Guided Diffusion Modelscited by 721
  16. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  17. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  18. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  19. 2024FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisioncited by 507
  20. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 498
  21. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  22. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  23. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  24. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  25. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
  26. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  27. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  28. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  29. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  30. 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 303
  31. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  32. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  33. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  34. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  35. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214
  36. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
  37. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  38. 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

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
  2. 2026Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
  3. 2025MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation
  4. 2024Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning
  5. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
  6. 2025Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
  7. 2026Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design
  8. 2024Edify 3D: Scalable High-Quality 3D Asset Generation