3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing

2026-06-05 · Source: Computer Vision and Pattern Recognition · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Computer Vision & Pattern Recognition, Gaming & Interactive Media · Depth: Expert, quick

Summary

3DMorph is a training-free framework designed for single-image-guided local 3D shape editing and morphing, addressing limitations in existing 3D editing tools that are often global, domain-specific, or focus on appearance. This method automatically localizes relevant 3D regions from an edited image, transferring 2D modifications to 3D while preserving unmodified areas. It also facilitates design exploration by enabling intermediate shape generation between original and edited objects. To evaluate editing quality, 3DMorph introduces Delta3D, an image-guided local 3D editing benchmark with paired ground-truth edits. Experimental results indicate that 3DMorph effectively translates intuitive 2D edits into 3D, outperforming current generative and editing methods.

Key takeaway

For 3D artists or designers seeking intuitive shape modification, 3DMorph offers a training-free solution to locally edit 3D models using simple 2D image modifications, overcoming limitations of global or appearance-focused tools. This approach streamlines your design iteration process, allowing you to quickly explore shape variations and refine models with precise, localized adjustments. Consider integrating this single-image-guided method to enhance your workflow efficiency.

Key insights

3DMorph enables intuitive local 3D shape editing from a single image, outperforming existing methods.

Principles

• Local 3D editing from 2D input is challenging.
• Preserving unmodified areas is key for local edits.
• Benchmarking 3D editing requires ground-truth pairs.

Method

3DMorph automatically localizes 3D regions from an edited image, transfers 2D modifications to 3D while preserving other areas, and generates intermediate shapes.

In practice

• Use single-image edits for 3D shape modification.
• Explore design variations via intermediate shape generation.
• Evaluate 3D editing with image-guided ground truth.

Topics

• 3D Shape Editing
• Single-Image Guidance
• Local 3D Morphing
• Computer Graphics
• Computer Vision
• Delta3D Benchmark

Best for: AI Scientist, Computer Vision Engineer, Research Scientist

Related on AIssential

• 3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing — 3DMorph enables precise local 3D shape editing and morphing from a single edited 2D image without training.
• Direct 3D-Aware Object Insertion via Decomposed Visual Proxies — DIRECT enables precise 3D-aware object insertion by decomposing appearance, geometry, and context guidance into independent generative pathways.
• Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data — BVE enables high-fidelity, text-guided 3D editing by integrating lightweight modules and a 3D masking strategy into a generative architecture.
• VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction — VGGT-Edit enables native 3D scene editing via depth-synchronized text injection and residual 3D geometric displacement prediction.
• GuideCAD: A Lightweight Multimodal Framework for 3D CAD Model Generation via Prefix Embedding — GuideCAD efficiently generates 3D CAD models by integrating visual and textual data via prefix embeddings and a pretrained LLM.
• Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data — The BVE framework improves 3D editing by using a custom dataset, lightweight modules, and an annotation-free masking strategy.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Computer Vision and Pattern Recognition.