mlsanityData to 14 Oct 2026

Generative Blocks World: Moving Things Around in Pictures

arXiv 2506.20703 ↗First posted 25 Jun 2025cs.GR cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

We describe Generative Blocks World to interact with the scene of a generated image by manipulating simple geometric abstractions. Our method represents scenes as assemblies of convex 3D primitives, and the same scene can be represented by different numbers of primitives, allowing an editor to move either whole structures or small details. Once the scene geometry has been edited, the image is generated by a flow-based method, which is conditioned on depth and a texture hint. Our texture hint takes into account the modified 3D primitives, exceeding the texture-consistency provided by existing techniques. These texture hints (a) allow accurate object and camera moves and (b) preserve the identity of objects. Our experiments demonstrate that our approach outperforms prior works in visual fidelity, editability, and compositional generalization.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 45 of its 60 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

45 of 60 references.

References · 45

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2023Segment Anythingcited by 8,234
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  6. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  7. 2024Depth Anything V2cited by 1,422
  8. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  10. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  11. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  12. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 343
33 more
  1. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  2. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 294
  3. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 219
  4. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  5. 2023DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Modelscited by 195
  6. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  7. 2019CvxNet: Learnable Convex Decompositioncited by 174
  8. 2024Stable Flow: Vital Layers for Training-Free Image Editingcited by 113
  9. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  10. 2018LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Imagecited by 95
  11. 2023LooseControl: Lifting ControlNet for Generalized Depth Conditioningcited by 68
  12. 2023OBJECT 3DIT: Language-guided 3D-aware Image Editingcited by 63
  13. 2023Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3Dcited by 59
  14. 2023Generative Models: What Do They Know? Do They Know Things? Let's Find Out!cited by 50
  15. 2024Image Sculpting: Precise Object Editing with 3D Geometry Controlcited by 45
  16. 2022Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenescited by 44
  17. 2023StyleGAN knows Normal, Depth, Albedo, and Morecited by 44
  18. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 38
  19. 2024LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relightingcited by 38
  20. 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generationcited by 35
  21. 2024GoodDrag: Towards Good Practices for Drag Editing with Diffusion Modelscited by 34
  22. 2024StableDrag: Stable Dragging for Point-based Image Editingcited by 28
  23. 2024Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generationcited by 18
  24. 2021Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Imagescited by 17
  25. 2024Editable Image Elements for Controllable Synthesiscited by 13
  26. 20253D-Fixup: Advancing Photo Editing with 3D Priorscited by 12
  27. 2023NVS-Adapter: Plug-and-Play Novel View Synthesis from a Single Imagecited by 11
  28. 2025Visual Jenga: Discovering Object Dependencies via Counterfactual Inpaintingcited by 11
  29. 2023Convex Decomposition of Indoor Scenescited by 7
  30. 20253D Object Manipulation in a Single Image using Generative Modelscited by 7
  31. 2023Dequantization and Color Transfer with Diffusion Modelscited by 4
  32. 2023Evaluate Geometry of Radiance Fields with Low-frequency Color Priorcited by 2
  33. 2024Denoising Monte Carlo Renders with Diffusion Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025Coupled Diffusion Sampling for Training-Free Multi-View Image Editingcited by 4
  2. 2026Thinking in Boxes: 3D Editing in Real Images Made Easycited by 0