mlsanityData to 7 Oct 2026

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

arXiv 2409.12957 ↗First posted 19 Sep 2024cs.CV cs.GRcited by 100

Not on the map. Why?

Abstract (arXiv)

The increasing demand for high-quality 3D assets across various industries necessitates efficient and automated 3D content creation. Despite recent advancements in 3D generative models, existing methods still face challenges with optimization speed, geometric fidelity, and the lack of assets for physically based rendering (PBR). In this paper, we introduce 3DTopia-XL, a scalable native 3D generative model designed to overcome these limitations. 3DTopia-XL leverages a novel primitive-based 3D representation, PrimX, which encodes detailed shape, albedo, and material field into a compact tensorial format, facilitating the modeling of high-resolution geometry with PBR assets. On top of the novel representation, we propose a generative framework based on Diffusion Transformer (DiT), which comprises 1) Primitive Patch Compression, 2) and Latent Primitive Diffusion. 3DTopia-XL learns to generate high-quality 3D assets from textual or visual inputs. We conduct extensive qualitative and quantitative experiments to demonstrate that 3DTopia-XL significantly outperforms existing methods in generating high-quality 3D assets with fine-grained textures and materials, efficiently bridging the quality gap between generative models and real-world applications.

Key facts. Cited by 100 papers in the map (data through 7 Oct 2026). Builds on 74 of its 87 references that are in the map. First posted on arXiv 19 Sep 2024.

Builds on

74 of 87 references.

References · 74

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2022Scalable Diffusion Models with Transformerscited by 5,931
  8. 2022Classifier-Free Diffusion Guidancecited by 5,717
  9. 2022Generative Adversarial Networkscited by 5,603
  10. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  12. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
38 more
  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  2. 2018Demystifying MMD GANscited by 1,268
  3. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  4. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  5. 2020On Layer Normalization in the Transformer Architecturecited by 906
  6. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  7. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  8. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  9. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  10. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  11. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  12. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  13. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  14. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  15. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  16. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  17. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  18. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  19. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  20. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  21. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  22. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  23. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  24. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  25. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  26. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
  27. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  28. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214
  29. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  30. 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
  31. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  32. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
  33. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 183
  34. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generationcited by 181
  35. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
  36. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  37. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  38. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 132

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 48; 2026: 45.

100 papers.

Sort:

By area:

  1. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  2. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 157
  3. 2025Native and Compact Structured Latents for 3D Generationcited by 157
  4. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  5. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  6. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 62
  7. 2025Efficient Part-level 3D Object Generation via Dual Volume Packingcited by 47
  8. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Imagescited by 41
  9. 2025PhysX-3D: Physical-Grounded 3D Asset Generationcited by 40
  10. 2025Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Cachingcited by 39
  11. 2025Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistencycited by 34
  12. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
38 more
  1. 2025Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesiscited by 33
  2. 2025PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Imagecited by 32
  3. 2024Material Anything: Generating Materials for Any 3D Object via Diffusioncited by 31
  4. 20254DNeX: Feed-Forward 4D Generative Modeling Made Easycited by 31
  5. 2025NANO3D: A Training-Free Approach for Efficient 3D Editing Without Maskscited by 29
  6. 2025DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundnesscited by 24
  7. 2025HiScene: Creating Hierarchical 3D Scenes with Isometric View Generationcited by 18
  8. 2024LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusioncited by 16
  9. 2024TAR3D: Creating High-Quality 3D Assets via Next-Part Predictioncited by 16
  10. 20243D representation in 512-Byte:Variational tokenizer is the key for autoregressive 3D generationcited by 10
  11. 2025ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latentscited by 10
  12. 2025SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modelingcited by 9
  13. 2025CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligencecited by 9
  14. 2025MeshRipple: Structured Autoregressive Generation of Artist-Meshescited by 8
  15. 2025Are We Ready for RL in Text-to-3D Generation? A Progressive Investigationcited by 8
  16. 2024ARM: Appearance Reconstruction Model for Relightable 3D Generationcited by 7
  17. 2025Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generationcited by 7
  18. 2026PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objectscited by 7
  19. 2026Feedforward 3D Editing Learns from Semantic-Part Transformationcited by 7
  20. 2025Textured 3D Regenerative Morphing with 3D Diffusion Priorcited by 6
  21. 2025Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Modelscited by 6
  22. 2025FreeMesh: Boosting Mesh Generation with Coordinates Mergingcited by 6
  23. 2025ART-DECO: Arbitrary Text Guidance for 3D Detailizer Constructioncited by 6
  24. 2025Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silkcited by 6
  25. 2025Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimizationcited by 6
  26. 2025SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materialscited by 5
  27. 2025MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layoutscited by 5
  28. 2025PhysGen: Physically Grounded 3D Shape Generation for Industrial Designcited by 5
  29. 2026PEGAsus: 3D Personalization of Geometry and Appearancecited by 5
  30. 2026MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstructioncited by 5
  31. 2025NeAR: Coupled Neural Asset-Renderer Stackcited by 4
  32. 2026MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphingcited by 4
  33. 2026Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphingcited by 4
  34. 2025Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validitycited by 3
  35. 2025Collaborative Multi-Modal Coding for High-Quality 3D Generationcited by 3
  36. 2025CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusioncited by 3
  37. 2025Few-step Flow for 3D Generation via Marginal-Data Transport Distillationcited by 2
  38. 2026HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependencecited by 2

50 most cited of 100 All 100 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
  2. 2024Boosting 3D Object Generation through PBR Materials
  3. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  4. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
  5. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scale
  6. 2026Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
  7. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
  8. 2026Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design