mlsanityData to 14 Oct 2026

Training-free Geometric Image Editing on Diffusion Models

arXiv 2507.23300 ↗First posted 31 Jul 2025cs.CVcited by 13

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

Abstract (arXiv)

We tackle the task of geometric image editing, where an object within an image is repositioned, reoriented, or reshaped while preserving overall scene coherence. Previous diffusion-based editing methods often attempt to handle all relevant subtasks in a single step, proving difficult when transformations become large or structurally complex. We address this by proposing a decoupled pipeline that separates object transformation, source region inpainting, and target region refinement. Both inpainting and refinement are implemented using a training-free diffusion approach, FreeFine. In experiments on our new GeoBench benchmark, which contains both 2D and 3D editing scenarios, FreeFine outperforms state-of-the-art alternatives in image fidelity, and edit precision, especially under demanding transformations. Code and benchmark are available at: https://github.com/CIawevy/FreeFine

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 70 of its 80 references that are in the map. First posted on arXiv 31 Jul 2025.

Builds on

70 of 80 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance17 Dec
  2. 2024MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement26 Aug
  3. 2024GeoDiffuser: Geometry-Based Image Editing with Diffusion Models22 Apr
  4. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion18 Mar
  5. 2024BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion11 Mar
  6. 2023Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D2 Dec
  7. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  8. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan

Other references · 62

  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. 2023Segment Anythingcited by 8,234
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  10. 2022Classifier-Free Diffusion Guidancecited by 5,847
  11. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  12. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
38 more
  1. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  3. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  5. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  6. 2015Spatial Transformer Networkscited by 1,429
  7. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  8. 2018Demystifying MMD GANscited by 1,293
  9. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  10. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  11. 2022Denoising Diffusion Restoration Modelscited by 963
  12. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  13. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  14. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  15. 2023Emergent Correspondence from Image Diffusioncited by 446
  16. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 340
  17. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 340
  18. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  19. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 294
  20. 2017VITON: An Image-based Virtual Try-on Networkcited by 286
  21. 2017Pose Guided Person Image Generationcited by 251
  22. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 219
  23. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 218
  24. 2023Style Aligned Image Generation via Shared Attentioncited by 216
  25. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  26. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 199
  27. 2023DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Modelscited by 195
  28. 2018Toward Characteristic-Preserving Image-based Virtual Try-On Networkcited by 192
  29. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  30. 2023SCLIP: Rethinking Self-Attention for Dense Vision-Language Inferencecited by 170
  31. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  32. 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
  33. 2016Deep Image Homography Estimationcited by 136
  34. 2023Cross-Image Attention for Zero-Shot Appearance Transfercited by 136
  35. 2024Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editingcited by 135
  36. 2024Training-Free Consistent Text-to-Image Generationcited by 125
  37. 2023Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulationcited by 62
  38. 2021Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editingcited by 54

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Renderingcited by 15
  2. 2026LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generationcited by 6
  3. 2026RewardFlow: Generate Images by Optimizing What You Rewardcited by 3
  4. 2026GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editingcited by 1
  5. 2026InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptationcited by 1
  6. 2026Thinking in Boxes: 3D Editing in Real Images Made Easycited by 0
  7. 2026BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editingcited by 0
  8. 2026RoPEMover: Depth-Aware Object Relocation via Positional Embeddingscited by 0
  9. 2026UniGen-AR: Unifying Visual Generation with Auto-Regressive Modelingcited by 0
  10. 2026ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inferencecited by 0
  11. 2026SpatialDiff: 3D-Aware Object Movement via Implicit Spatial Modelingcited by 0
  12. 2026Stabilizing Camera-Controlled Novel View Synthesis at Inference Timecited by 0
1 more
  1. 2026AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognitioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising
  2. 2024Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors
  3. 2024Towards a Training Free Approach for 3D Scene Editing
  4. 2026Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers
  5. 2025FreeInsert: Personalized Object Insertion with Geometric and Style Control
  6. 2025Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers
  7. 20243D-Consistent Image Inpainting with Diffusion Models
  8. 2025PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement