3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing
Not on the map. Why?
Abstract (arXiv)
Despite recent progress in 3D generation, intuitive editing of existing shapes remains limited. Unlike images, which benefit from well-established inpainting tools, general 3D objects such as meshes still lack simple and effective methods for local shape editing. Existing approaches are often global, domain-specific, require complex user interaction, or focus on appearance (color and texture) rather than geometry. We introduce 3DMorph, a training-free framework for single-image-guided local 3D shape editing and morphing. Given an edited image showing a desired shape modification, our method automatically localizes the relevant 3D region and transfers 2D modifications to 3D while preserving unmodified areas. 3DMorph also enables intermediate shape generation between the original and edited objects, facilitating design exploration. To benchmark editing quality, we introduce Delta3D, an image-guided local 3D editing benchmark with paired ground-truth edits. Experimental results show that 3DMorph translates intuitive 2D edits into 3D, outperforming state-of-the-art generative and editing methods.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 5 Jun 2026.
Builds on
36 of 45 references.
References · 36
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
- 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
- 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
- 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
- 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
- 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
- 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
- 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
- 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 157
- 2025Native and Compact Structured Latents for 3D Generationcited by 157
24 more
- 2023Vox-E: Text-guided Voxel Editing of 3D Objectscited by 114
- 2023TextDeformer: Geometry Manipulation using Text Guidancecited by 94
- 2021NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Gocited by 81
- 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 77
- 2023FocalDreamer: Text-driven 3D Editing via Focal-fusion Assemblycited by 75
- 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
- 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 60
- 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
- 2025VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Spacecited by 40
- 2023SHAP-EDITOR: Instruction-guided Latent 3D Editing in Secondscited by 36
- 2025NANO3D: A Training-Free Approach for Efficient 3D Editing Without Maskscited by 29
- 20243D Mesh Editing using Masked LRMscited by 17
- 2023Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapescited by 14
- 2025CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generationcited by 14
- 2020Hamiltonian Dynamics for Real-World Shape Interpolationcited by 13
- 2024SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimationcited by 12
- 2022LADIS: Language Disentanglement for 3D Shape Editingcited by 10
- 2025Towards Scalable and Consistent 3D Editingcited by 9
- 2023SENS: Part-Aware Sketch-based Implicit Neural Shape Modelingcited by 8
- 2025AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flowscited by 8
- 20254Deform: Neural Surface Deformation for Robust Shape Interpolationcited by 7
- 2025Native 3D Editing with Full Attentioncited by 3
- 2025GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generationcited by 2
- 2025Why Are You Wrong? Counterfactual Explanations for Language Grounding with 3D Objectscited by 1
Built on by
Not cited yet.