发表机构
The University of Hong Kong; Shenzhen Loop Area Institute; Shanghai Innovation Institute; Sun Yat-Sen University（香港大学; 深圳河套学院; 上海创新研究院; 中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Alchemy3D框架，含百万级数据集Alchemy3D-1M和生成流模型系列，以及GEdit3D-Bench基准，实现通用3D资产编辑，在编辑保真度、源保留和视觉质量上优于现有方法。
AI 中文摘要
尽管近期的3D生成模型能够生成越来越逼真的资产，但可控的3D资产编辑仍然具有挑战性。现有方法受限于训练数据稀缺、源感知建模不足以及缺乏实用的评估协议。为解决这些局限，我们提出了Alchemy3D，一个用于训练和评估通用3D资产编辑器的统一框架，涵盖数据构建、模型架构和基准评估。具体而言，我们整理了Alchemy3D-1M，一个包含125万资产和138万编辑对、覆盖七种编辑类型的大规模3D编辑数据集。基于该数据，我们训练了一系列生成流模型，用于通用3D资产编辑。该模型系列支持图像和文本条件编辑、少步推理，并可迁移至多视图3D部件分割。我们还引入了GEdit3D-Bench，一个具有多维评估协议的大规模开放世界基准。在现有和新引入的基准上，我们的方法在编辑保真度、源保留和视觉质量的大多数指标上优于先前方法。
英文摘要
Although recent 3D generative models produce increasingly realistic assets, controllable 3D asset editing remains challenging. Existing methods are limited by scarce training data, insufficient source-aware modeling, and a lack of practical evaluation protocols. To address these limitations, we present Alchemy3D, a unified framework for training and evaluating versatile 3D asset editors that covers data construction, model architecture, and benchmark evaluation. Specifically, we curate Alchemy3D-1M, a large-scale 3D editing dataset containing 1.25M assets and 1.38M editing pairs across seven editing types. On this data, we train a family of generative flow models for general-purpose 3D asset editing. The model family supports image- and text-conditioned editing, few-step inference, and transfer to multi-view 3D part segmentation. We further introduce GEdit3D-Bench, a large-scale, open-world benchmark with a multi-dimensional evaluation protocol. Across existing and newly introduced benchmarks, our method outperforms prior methods on most metrics of editing fidelity, source preservation, and visual quality.
