mlsanityData to 7 Oct 2026

SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation

arXiv 2509.12721 ↗First posted 16 Sep 2025cs.CVcited by 5

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

Abstract (arXiv)

Existing single-view 3D generative models typically adopt multiview diffusion priors to reconstruct object surfaces, yet they remain prone to inter-view inconsistencies and are unable to faithfully represent complex internal structure or nontrivial topologies. In particular, we encode geometry information by projecting it onto a bounding sphere and unwrapping it into a compact and structural multi-layer 2D Spherical Projection (SP) representation. Operating solely in the image domain, SPGen offers three key advantages simultaneously: (1) Consistency. The injective SP mapping encodes surface geometry with a single viewpoint which naturally eliminates view inconsistency and ambiguity; (2) Flexibility. Multi-layer SP maps represent nested internal structures and support direct lifting to watertight or open 3D surfaces; (3) Efficiency. The image-domain formulation allows the direct inheritance of powerful 2D diffusion priors and enables efficient finetuning with limited computational resources. Extensive experiments demonstrate that SPGen significantly outperforms existing baselines in geometric quality and computational efficiency.

Key facts. Cited by 5 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 61 of its 89 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

61 of 89 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation21 Jan
  2. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets30 May
  3. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer23 May
  4. 2024X-Ray: A Sequential 3D Representation For Generation22 Apr
  5. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image18 Mar
  6. 2023PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models18 Dec
  7. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model10 Nov
  8. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  9. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  10. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  12. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
3 more
  1. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  2. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  3. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 46

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  10. 2022Scalable Diffusion Models with Transformerscited by 5,931
  11. 2017Neural Discrete Representation Learningcited by 4,650
  12. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
34 more
  1. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  3. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  4. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  6. 2020Convolutional Occupancy Networkscited by 760
  7. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  8. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  9. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  10. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  11. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  12. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  13. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  14. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 204
  15. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  16. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
  17. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
  18. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  19. 2020Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Imagescited by 101
  20. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  21. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  22. 2024Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scalecited by 87
  23. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  24. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 75
  25. 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
  26. 2023360-Degree Panorama Generation from Few Unregistered NFoV Imagescited by 42
  27. 2018Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layerscited by 33
  28. 2023Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generationcited by 33
  29. 2023Disentangled Clothed Avatar Generation from Text Descriptionscited by 33
  30. 2021Deep Multi-Task Learning for Joint Localization, Perception, and Predictioncited by 22
  31. 2024Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representationcited by 17
  32. 2024SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstructioncited by 10
  33. 2023SDF-3DGAN: A 3D Object Generative Method Based on Implicit Signed Distance Functioncited by 7
  34. 2022HORIZON: High-Resolution Semantically Controlled Panorama Synthesiscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025UniSER: A Foundation Model for Unified Soft Effects Removalcited by 5
  2. 2026MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priorscited by 5
  3. 2026DiffHDR: Re-Exposing LDR Videos with Video Diffusion Modelscited by 3
  4. 2026Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editingcited by 2
  5. 2026Beyond Thinking: Imagining in 360^circ for Humanoid Visual Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors
  2. 2024An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion
  3. 2025Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image
  4. 2024Direct and Explicit 3D Generation from a Single Image
  5. 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
  6. 2024Vista3D: Unravel the 3D Darkside of a Single Image
  7. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior
  8. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion