Vinedresser3D: Agentic Text-guided 3D Editing

TL;DR

Vinedresser3D is a novel framework that enables high-quality, precise, and coherent text-guided editing of 3D assets by operating directly in the latent space of a 3D generative model, integrating multimodal understanding and visual guidance.

Contribution

It introduces an agentic, multi-step approach combining language understanding, view selection, visual guidance, and latent space inpainting for 3D editing, outperforming prior methods.

Findings

Outperforms prior baselines in automatic metrics

Achieves higher human preference scores

Enables mask-free, precise 3D editing

Abstract

Text-guided 3D editing aims to modify existing 3D assets using natural-language instructions. Current methods struggle to jointly understand complex prompts, automatically localize edits in 3D, and preserve unedited content. We introduce Vinedresser3D, an agentic framework for high-quality text-guided 3D editing that operates directly in the latent space of a native 3D generative model. Given a 3D asset and an editing prompt, Vinedresser3D uses a multimodal large language model to infer rich descriptions of the original asset, identify the edit region and edit type (addition, modification, deletion), and generate decomposed structural and appearance-level text guidance. The agent then selects an informative view and applies an image editing model to obtain visual guidance. Finally, an inversion-based rectified-flow inpainting pipeline with an interleaved sampling module performs editing in the 3D latent space, enforcing prompt alignment while maintaining 3D coherence and unedited regions. Experiments on diverse 3D edits demonstrate that Vinedresser3D outperforms prior baselines in both automatic metrics and human preference studies, while enabling precise, coherent, and mask-free 3D editing.