EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning

2026-07-08

AI Summary

This work addresses the challenge of achieving high-quality, locally consistent 3D object editing given only a coarse 3D bounding box and a 2D reference image. To this end, the authors propose a novel editing framework that introduces a region-aware adaptive loss function to enhance optimization in difficult regions and balance the trade-off between edited and preserved areas. The approach further incorporates a scale-based 3D mask data augmentation strategy, a mechanism for filtering implausible editing pairs, and introduces the first large-scale part-level 3D editing dataset. Experimental results demonstrate that the proposed method significantly outperforms existing approaches in both visual quality and quantitative metrics, enabling more natural, efficient, and high-fidelity local 3D editing.

Abstract

Local editing of 3D objects remains a long-standing challenge. When interacting with 3D content, humans naturally tend to specify a coarse region of interest for modification rather than defining precise editing boundaries. However, previous methods rely on fully edited 2D images, precise 3D masks, or redundant pipelines, which present a gap. To bridge this gap, we propose EditVerse3D, a novel 3D editing framework that enables high-quality object editing under such coarse guidance. Our approach takes as input a 3D object to be edited, a coarse 3D bounding box indicating the target region, and a reference 2D image describing the desired modification. It produces a coherent, high-fidelity edited 3D object. To facilitate this editing, we introduce a novel region-aware adaptive loss that emphasizes hard-to-learn regions and balances the objective between target and preserved areas. Complementing our loss function, we enhance model robustness and generalization through targeted data augmentations, such as training with scaled 3D masks and filtering out unrealistic editing pairs. We construct a large-scale 3D editing dataset derived from parts information. Extensive experiments demonstrate that EditVerse3D achieves superior visual quality and quantitative performance compared to existing 3D editing approaches. Please visit our project page at https://editverse3d.github.io.

Problem

• 3D object editing
• local editing
• coarse guidance
• region-aware learning
• high-fidelity editing

Innovation

• region-aware learning
• 3D object editing
• adaptive loss
• coarse guidance
• data augmentation