mlsanityData to 7 Oct 2026

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

arXiv 2505.14521 ↗First posted 20 May 2025cs.CVcited by 84

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

High-fidelity 3D object synthesis remains significantly more challenging than 2D image generation due to the unstructured nature of mesh data and the cubic complexity of dense volumetric grids. Existing two-stage pipelines-compressing meshes with a VAE (using either 2D or 3D supervision), followed by latent diffusion sampling-often suffer from severe detail loss caused by inefficient representations and modality mismatches introduced in VAE. We introduce Sparc3D, a unified framework that combines a sparse deformable marching cubes representation Sparcubes with a novel encoder Sparconv-VAE. Sparcubes converts raw meshes into high-resolution (10243) surfaces with arbitrary topology by scattering signed distance and deformation fields onto a sparse cube, allowing differentiable optimization. Sparconv-VAE is the first modality-consistent variational autoencoder built entirely upon sparse convolutional networks, enabling efficient and near-lossless 3D reconstruction suitable for high-resolution generative modeling through latent diffusion. Sparc3D achieves state-of-the-art reconstruction fidelity on challenging inputs, including open surfaces, disconnected components, and intricate geometry. It preserves fine-grained shape details, reduces training and inference cost, and integrates naturally with latent diffusion models for scalable, high-resolution 3D generation.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 29 of its 40 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

29 of 40 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models10 Feb
  2. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation21 Jan
  3. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders23 Dec
  4. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets30 May
  5. 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner23 May
  6. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  7. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion12 Dec
  8. 2022Fast Point Cloud Generation with Straight Flows4 Dec
  9. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 20

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  4. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  5. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  6. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  7. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  8. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 257
  9. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  10. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  11. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 183
  12. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
8 more
  1. 2023Flexible Isosurface Extraction for Gradient-Based Mesh Optimizationcited by 138
  2. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 116
  3. 2024MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenizationcited by 102
  4. 2024LLaMA-Mesh: Unifying 3D Mesh Generation with Language Modelscited by 87
  5. 2024Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scalecited by 87
  6. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  7. 2024Advances in 3D Generation: A Surveycited by 62
  8. 20233D VR Sketch Guided 3D Shape Prototyping and Explorationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 26; 2026: 58.

84 papers.

Sort:

By area:

  1. 2025Native and Compact Structured Latents for 3D Generationcited by 157
  2. 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 43
  3. 2025TexVerse: A Universe of 3D Objects with High-Resolution Texturescited by 41
  4. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 41
  5. 2025VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Spacecited by 40
  6. 2025ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generationcited by 30
  7. 2025UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generationcited by 20
  8. 2025ShapeGen4D: Towards High Quality 4D Shape Generation from Videoscited by 20
  9. 2026ShapeR: Robust Conditional 3D Shape Generation from Casual Capturescited by 19
  10. 2025LL3M: Large Language 3D Modelerscited by 18
  11. 2025UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinementcited by 16
  12. 2026Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesiscited by 15
38 more
  1. 2025QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Modelscited by 11
  2. 2026Pixal3D: Pixel-Aligned 3D Generation from Imagescited by 11
  3. 2026LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtentscited by 10
  4. 2025UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latentscited by 9
  5. 2025MeshRipple: Structured Autoregressive Generation of Artist-Meshescited by 8
  6. 2025Part-X-MLLM: Part-aware 3D Multimodal Large Language Modelcited by 6
  7. 2026LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flowcited by 6
  8. 2025MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generationcited by 5
  9. 2025Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surfacecited by 4
  10. 2025LaFiTe: A Generative Latent Field for 3D Native Texturingcited by 4
  11. 2026MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphingcited by 4
  12. 2026Generative 3D Gaussians with Learned Density Controlcited by 4
  13. 2025CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generationcited by 3
  14. 2025Self-Evolving 3D Scene Generation from a Single Imagecited by 3
  15. 2026RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Spacecited by 3
  16. 2026Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimationcited by 3
  17. 2025LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioningcited by 2
  18. 2025UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulationcited by 2
  19. 2026CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Modelscited by 2
  20. 2026Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generationcited by 2
  21. 2026LiTo: Surface Light Field Tokenizationcited by 2
  22. 2026TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unificationcited by 2
  23. 2026LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windowscited by 2
  24. 2026Hitem3D 2.0: Multi-View Guided Native 3D Texture Generationcited by 2
  25. 2026DVD: Discrete Voxel Diffusion for 3D Generation and Editingcited by 2
  26. 2026WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenescited by 2
  27. 2026One Video, One World: Turning Monocular Video into Physical 4D Scenescited by 2
  28. 2026DualBrep: A Dual-Field Continuous Representation for B-rep Modellingcited by 2
  29. 2025PoseMaster: A Unified 3D Native Framework for Stylized Pose Generationcited by 1
  30. 2025Jigsaw3D: Disentangled 3D Style Transfer via Patch Shuffling and Maskingcited by 1
  31. 2026NuiWorld: Exploring a Scalable Framework for End-to-End Controllable World Generationcited by 1
  32. 2026AssetFormer: Modular 3D Assets Generation with Autoregressive Transformercited by 1
  33. 2026Text-Image Conditioned 3D Generationcited by 1
  34. 2026SARe: Structure-Aware Generative 3D Fragment Reassemblycited by 1
  35. 2026Know3D: Prompting 3D Generation with Knowledge from Vision-Language Modelscited by 1
  36. 2026High-Fidelity Single-Image Head Modeling with Industry-Grade Topologycited by 1
  37. 2026Velocity-Space 3D Asset Editingcited by 1
  38. 2026SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generationcited by 1

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images
  2. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model
  3. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
  4. 2025Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models
  5. 2025LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework
  6. 2026MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces
  7. 2025Hyper3D: Efficient 3D Representation via Hybrid Triplane and Octree Feature for Enhanced 3D Shape Variational Auto-Encoders
  8. 2023Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models