Research map / 3D vision / 3D generation
ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGS
Yuhuan Xie, Aoxuan Pan, Yi-Hua Huang, Chirui Chang, Peng Dai, Xin Yu, Xiaojuan Qi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| lift object to 3DGS and edit with ARAP-constrained drag instead of 2D drag/mask editing | ObjectMorpher · User study, 8 editing tasks | Guidance Following score: 1.68 (DragDiffusion) / 1.83 (Anydoor) -> 4.71 | Improved |
| evaluate with automatic fidelity metrics (LPIPS/SIFID) that reward minimal edits | DragDiffusion, Anydoor · 50-subject editing benchmark | LPIPS / SIFID | Mixed |
| use 3DGS output of TRELLIS instead of its mesh decoder (ablation) | ObjectMorpher · 3D representation ablation (qualitative) | rendering quality | Improved |
| add Generative Composition (diffusion refinement) after compositing the rendered object (ablation) | ObjectMorpher · Generative composition ablation (qualitative) | visual coherence | Improved |
| use ARAP rotation-invariant constraint instead of Laplacian-only deformation (ablation) | ObjectMorpher · Editing constraint ablation (qualitative) | local geometry preservation | Improved |
| use geodesic-distance graph instead of Euclidean-distance graph for deformable graph (ablation) | ObjectMorpher · Graph construction (qualitative) | deformation quality | Improved |
Closest papers by meaning
- 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing (ICLR 2025 · similarity 0.88)
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- Image Sculpting: Precise Object Editing with 3D Geometry Control (CVPR 2024 · similarity 0.88)
- 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting (ICLR 2025 · similarity 0.87)
- CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion (CVPR 2025 · similarity 0.87)
- Thinking in Boxes: 3D Editing in Real Images Made Easy (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
