Search papers, labs, and topics across Lattice.
EditFlow3D introduces a training-free framework for local editing of 3D assets that effectively preserves the structure and appearance of non-target regions while allowing precise target localization. By leveraging a visual language model (VLM) to interpret editing instructions, it automatically generates a visual guidance image and a refined 3D editing mask, facilitating localized edits in the native representation space of a pretrained 3D generative model. Evaluation against the newly introduced EditFlow-Bench shows that EditFlow3D outperforms existing methods in both accuracy of target-region editing and preservation of non-target regions.
EditFlow3D achieves superior local editing in 3D assets by maintaining non-target region integrity while precisely executing edits.
Controllable local editing of 3D assets requires precise target localization and appropriate visual guidance. However, existing methods lack a simple yet accurate way to obtain 3D masks and struggle to achieve the desired edit while faithfully preserving the structure and appearance of non-target regions. To address these challenges, we present EditFlow3D, a training-free framework for local 3D editing. Given a source asset and an edit instruction, a VLM-driven workflow interprets the editing intent and automatically constructs a visual guidance image and a refined 3D editing mask, enabling localized editing in the native representation space of a pretrained 3D generative model. Specifically, mask-guided differential flow focuses the edit on the target region, while step-wise trajectory preservation maintains consistency between non-target regions and the source asset without directly replacing intermediate features. Since the existing Edit3D-Bench covers only a limited range of local editing categories, we further introduce EditFlow-Bench as a complementary benchmark encompassing a broader variety of structural and appearance edits, and evaluate EditFlow3D on both benchmarks. Quantitative results, qualitative comparisons, and a user study demonstrate that EditFlow3D achieves more accurate target-region editing and better preserves non-target regions than existing 3D editing methods.
