Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGS Models

Yuhuan Xie, Aoxuan Pan, Yi-Hua Huang, Chirui Chang, Peng Dai, Xin Yu, Xiaojuan Qi

Abstract

Achieving precise, object-level control in image editing remains challenging: 2D methods lack 3D awareness and often yield ambiguous or implausible results, while existing 3D-aware approaches rely on heavy optimization or incomplete monocular reconstructions. We present ObjectMorpher, a unified, interactive framework that converts ambiguous 2D edits into geometry-grounded operations. ObjectMorpher lifts target instances with an image-to-3D generator into editable 3D Gaussian Splatting (3DGS), enabling fast, identity-preserving manipulation. Users drag control points; a graph-based non-rigid deformation with as-rigid-as-possible (ARAP) constraints ensures physically sensible shape and pose changes. A composite diffusion module harmonizes lighting, color, and boundaries for seamless reintegration. Across diverse categories, ObjectMorpher delivers fine-grained, photorealistic edits with superior controllability and efficiency, outperforming 2D drag and 3D-aware baselines on KID, LPIPS, SIFID, and user preference.

ObjectMorpher: 3D-Aware Image Editing via Deformable 3DGS Models

Abstract

Achieving precise, object-level control in image editing remains challenging: 2D methods lack 3D awareness and often yield ambiguous or implausible results, while existing 3D-aware approaches rely on heavy optimization or incomplete monocular reconstructions. We present ObjectMorpher, a unified, interactive framework that converts ambiguous 2D edits into geometry-grounded operations. ObjectMorpher lifts target instances with an image-to-3D generator into editable 3D Gaussian Splatting (3DGS), enabling fast, identity-preserving manipulation. Users drag control points; a graph-based non-rigid deformation with as-rigid-as-possible (ARAP) constraints ensures physically sensible shape and pose changes. A composite diffusion module harmonizes lighting, color, and boundaries for seamless reintegration. Across diverse categories, ObjectMorpher delivers fine-grained, photorealistic edits with superior controllability and efficiency, outperforming 2D drag and 3D-aware baselines on KID, LPIPS, SIFID, and user preference.

Paper Structure

This paper contains 25 sections, 5 equations, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Lifting 2D Pixels to 3DGS
  5. Physics-Plausible Interactive Editing
  6. Deformable Graph Construction
  7. Rigidity-Constrained Deformation
  8. Dense Gaussian deformation.
  9. Generative Composition and Refinement
  10. Experiment
  11. Implementation Details
  12. Evaluation Datasets and Baselines
  13. Datasets.
  14. Baselines.
  15. Evaluation Protocol.
  16. ...and 10 more sections

Figures (8)

  • Figure 1: Unlike text-based methods that fail to localize subjects or interpret geometry, ObjectMorpher uses direct 3D manipulation with real-time interaction. This ensures precise edits while preserving the object's identity and background.
  • Figure 2: Overview of our image editing pipeline. The object is lifted from 2D pixels to high-fidelity 3DGS. Real-time editing with local rigidity is applied based on user input. The object is then repositioned, and a generative model refines the edits for harmonious results.
  • Figure 3: Comparison of graph connections based on Euclidean distance and geodesic distance.
  • Figure 4: Illustration of the training data preparation and the pipeline of our generative composition model.
  • Figure 5: Qualitative comparisons. We show results on 8 subjects (rows) across 5 methods (columns). Our method (Ours) is the only one that faithfully follows the non-rigid user guidance while maintaining photorealism. 2D methods fail to perform the 3D-aware edit, producing results nearly identical to the origin.
  • ...and 3 more figures