mlsanityData to 14 Oct 2026

XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

arXiv 2312.03806 ↗First posted 6 Dec 2023cs.CV cs.GR cs.LGcited by 189

Not on the map. Why?

Cited by 54 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present XCube (abbreviated as X3), a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of voxels with a finest effective resolution of up to 10243 in a feed-forward fashion without time-consuming test-time optimization. To achieve this, we employ a hierarchical voxel latent diffusion model which generates progressively higher resolution grids in a coarse-to-fine manner using a custom framework built on the highly efficient VDB data structure. Apart from generating high-resolution objects, we demonstrate the effectiveness of XCube on large outdoor scenes at scales of 100m×100m with a voxel size as small as 10cm. We observe clear qualitative and quantitative improvements over past approaches. In addition to unconditional generation, we show that our model can be used to solve a variety of tasks such as user-guided editing, scene completion from a single scan, and text-to-3D. The source code and more results can be found at https://research.nvidia.com/labs/toronto-ai/xcube/.

Key facts. Cited by 189 papers in the map (data through 14 Oct 2026). Builds on 66 of its 81 references that are in the map. First posted on arXiv 6 Dec 2023.

Builds on

66 of 81 references.

References · 66

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  11. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  12. 2015Variational Inference with Normalizing Flowscited by 2,170
38 more
  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  2. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  3. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  4. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  5. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  7. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  9. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  10. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  11. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  12. 2020Convolutional Occupancy Networkscited by 761
  13. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  14. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 699
  15. 2021Score-based Generative Modeling in Latent Spacecited by 636
  16. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  17. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  18. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  19. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  20. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  21. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  22. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  23. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  24. 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 304
  25. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  26. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  27. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 269
  28. 2023Scalable 3D Captioning with Pretrained Modelscited by 203
  29. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  30. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generationcited by 183
  31. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 147
  32. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  33. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 130
  34. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  35. 2023Vox-E: Text-guided Voxel Editing of 3D Objectscited by 115
  36. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
  37. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  38. 2023Neural Kernel Surface Reconstructioncited by 104

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 29; 2025: 75; 2026: 85.

189 papers.

Sort:

By area:

  1. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  2. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  3. 2025SAM 3D: 3Dfy Anything in Imagescited by 247
  4. 2025Native and Compact Structured Latents for 3D Generationcited by 175
  5. 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 123
  6. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 110
  7. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusioncited by 101
  8. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 98
  9. 2025Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modelingcited by 89
  10. 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 84
  11. 2025Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Modelscited by 84
  12. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 79
38 more
  1. 20253D and 4D World Modeling: A Surveycited by 67
  2. 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplatscited by 60
  3. 2024InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Modelscited by 56
  4. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Modelcited by 55
  5. 2024LT3SD: Latent Trees for 3D Scene Diffusioncited by 55
  6. 2025DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generationcited by 50
  7. 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 44
  8. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 44
  9. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 44
  10. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 41
  11. 2024DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenescited by 38
  12. 2025Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesiscited by 33
  13. 2024SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generationcited by 24
  14. 2025Generating Physically Stable and Buildable Brick Structures from Textcited by 24
  15. 2024fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligencecited by 23
  16. 2025Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assetscited by 22
  17. 2025X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllabilitycited by 20
  18. 2025UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generationcited by 20
  19. 2025MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generationcited by 19
  20. 2025Nautilus: Locality-aware Autoencoder for Scalable Mesh Generationcited by 18
  21. 2024LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusioncited by 16
  22. 2025Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusioncited by 16
  23. 2025WorldGrow: Generating Infinite 3D Worldcited by 16
  24. 2024Atlas Gaussians Diffusion for 3D Generationcited by 15
  25. 2025HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editingcited by 15
  26. 2025VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modelingcited by 14
  27. 2025Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenizationcited by 13
  28. 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Graspingcited by 13
  29. 2025CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Drivingcited by 12
  30. 2025Assembler: Scalable 3D Part Assembly via Anchor Point Diffusioncited by 12
  31. 2024DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flowcited by 11
  32. 2025MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generationcited by 11
  33. 2026HY3D-Bench: Generation of 3D Assetscited by 11
  34. 2026PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objectscited by 11
  35. 2024Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodingscited by 10
  36. 20243D Shape Tokenization via Latent Flow Matchingcited by 10
  37. 2025SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understandingcited by 10
  38. 2026LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtentscited by 10

50 most cited of 189 All 189 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
  2. 2026SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation
  3. 2024Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
  4. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance
  5. 2025DreamCube: 3D Panorama Generation via Multi-plane Synchronization
  6. 2026RGBX-Next: Towards Realistic Generative Rendering from G-Buffers
  7. 2023MeshDiffusion: Score-based Generative 3D Mesh Modeling
  8. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models