mlsanityData to 7 Oct 2026

3D, point cloud and scene generation

1,593 papers4 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: diffusion, generation, image, scene, multi-view

Key facts. 3D, point cloud and scene generation: 1,593 papers on arXiv since 2021 (data through 7 Oct 2026). 641 of its 1,593 mapped papers (40%) cite “DreamFusion: Text-to-3D using 2D Diffusion” (2022, arXiv 2209.14988). 413 of its 1,593 mapped papers (26%) cite “Zero-1-to-3: Zero-shot One Image to 3D Object” (2023, arXiv 2303.11328). 26 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

26 new papers, 17 Sep – 7 Oct; 4 this week.

  1. This week · 4
  2. Relational Abstractions for Spatial Reasoning with Diffusion Models also fits: Image generation, text-to-image and editing
  3. MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces
  4. 4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction
  5. PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation
  6. Earlier · 22
  7. EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder also fits: Inverse problems and image restoration
  8. SymRegFlow: Symmetry-Regularized Flow Matching for Video World Models also fits: Video generation
  9. DAGS: Disentangled Appearance-and-Geometry Steering of a Frozen Image DiT for Temporally Stabilized Generative Rendering
  10. DiDE:Direct Injection with Color-Texture DEcoupling for 3D Stylization
  11. Geometric Similarity in VLM Low-Level Vision Representations also fits: Image generation, text-to-image and editing
  12. Texture Space Material Diffusion
All 26
  1. PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion also fits: Diffusion foundations and sampling
  2. BTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D Generation
  3. LoRA Direction Extraction for Controllable Light Toggling in FLUX.1 Kontext
  4. TaoFlowForge: Progressive Native Mesh Generation via Cascaded Flow Matching
  5. Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion also fits: Image generation, text-to-image and editing
  6. FILIGREE3D: Scaling Sparse Latent Flow Matching for Ultra-High-Resolution Image-to-3D Generation
  7. ReGDiff: Guided Diffusion in Regulated Latent Space for Exploring Metamaterial Voxel Geometry
  8. VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis
  9. QuacamFM: Quaternion-Constrained Flow Matching for Camera Pose Estimation
  10. Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning also fits: Inverse problems and image restoration
  11. DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume Rendering
  12. ZoomDiff: A High-Fidelity Diffusion Model for Dual-Camera Smooth Zooming
  13. PhysReflect: Geometry and Perception Guided Diffusion for Physically-Plausible Mirror Reflections
  14. 4DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors
  15. Physically Based Rendering in the Latent Space
  16. Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model also fits: Inverse problems and image restoration

Foundations

Most cited by papers here

  1. DreamFusion: Text-to-3D using 2D Diffusion2022cited by 641 here
  2. Zero-1-to-3: Zero-shot One Image to 3D Object2023cited by 413 here
  3. Magic3D: High-Resolution Text-to-3D Content Creation2022cited by 370 here
  4. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation2023cited by 335 here
  5. MVDream: Multi-view Diffusion for 3D Generation2023cited by 294 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020Denoising Diffusion Probabilistic Modelscited by 993 here
  2. 2020Denoising Diffusion Implicit Modelscited by 574 here
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 378 here
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 1,068 here
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 321 here
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 446 here
  7. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 221 here
  8. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 370 here
  9. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 200 here
  10. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 413 here
  11. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 335 here
  12. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 294 here
  13. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 217 here
  14. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 202 here
10 more it builds on, not in this chain
  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 328 here
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 191 here
  3. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 231 here
  4. 2022Classifier-Free Diffusion Guidancecited by 323 here
  5. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 641 here
  6. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 221 here
  7. 2022Scalable Diffusion Models with Transformerscited by 207 here
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 488 here
  9. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 234 here
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 209 here

The 24 most cited of 2,463.

Browse

30 of 1,593, ranked 6–35

  1. 6Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation2023234
  2. 7Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation2022221
  3. 8SyncDreamer: Generating Multiview-consistent Images from a Single-view Image2023217
  4. 9Wonder3D: Single Image to 3D using Cross-Domain Diffusion2023202
  5. 10Point-E: A System for Generating 3D Point Clouds from Complex Prompts2022200
  6. 11Diffusion Probabilistic Models for 3D Point Cloud Generation2021191
  7. 12LION: Latent Point Diffusion Models for 3D Shape Generation2022177
  8. 13RePaint: Inpainting using Denoising Diffusion Probabilistic Models2022176
  9. 14Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model2023170
  10. 15One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization2023163
All 30
  1. 16Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors2023141
  2. 17Novel View Synthesis with Diffusion Models2022121
  3. 18Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior2023119
  4. 19CAT3D: Create Anything in 3D with Multi-View Diffusion Models2024116
  5. 20SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion2024100
  6. 21TEXTure: Text-Guided Texturing of 3D Shapes202398
  7. 223D Neural Field Generation using Triplane Diffusion202297
  8. 23Generative Novel View Synthesis with 3D-Aware Diffusion Models202396
  9. 24Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion202294
  10. 253DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models202392
  11. 26DiffRF: Rendering-Guided 3D Radiance Field Diffusion202292
  12. 27ReconFusion: 3D Reconstruction with Diffusion Priors202389
  13. 28ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation202388
  14. 29Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model202387
  15. 30ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis202485
  16. 31One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion202385
  17. 32CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets202478
  18. 33Text2Tex: Text-driven Texture Synthesis via Diffusion Models202378
  19. 34Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation202372
  20. 35RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation202269