用2D图像和初始3D形状，生成细节更丰富的可控3D模型。
MeshReGen: A Unified 3D Geometry Regeneration Framework
- 基于VecSet的条件机制，可精细更新输入几何体。
- 在增强、重建、编辑任务中均达当前最优效果。
- 无需标注数据，从现成3D数据集自学习再生先验。
我们研究从2D图像和初始3D形状中再生3D物体的问题。现有3D生成方法多为单次生成，对文本或图像生成3D对象时控制能力有限。本文提出MeshReGen，一种以初始3D形状为条件的3D再生框架。该设计支持多种实用任务，包括3D增强、重建与编辑。其核心是基于VecSet的新条件机制，可一致地更新或改进输入几何体的细粒度细节。MeshReGen通过自监督预训练任务和数据增强，从现成3D数据集中学习通用再生先验，无需额外标注。我们在几何一致性与细粒度质量上进行评估，在多个可控3D生成任务中达到当前最优性能。
原文摘要 · Abstract (English)
We consider the problem of regenerating 3D objects from 2D images and initial 3D shapes. Most 3D generators operate in a one-shot fashion, converting text or images to a 3D object with limited controllability. We introduce instead MeshReGen, a 3D regenerator that is conditioned on an initial 3D shape. This conceptually simple formulation allows us to support numerous useful tasks, including 3D enhancement, reconstruction, and editing. MeshReGen uses a new conditioning mechanism based on VecSet, which allows the regenerator to update or improve the input geometry with consistent fine-grained details. MeshReGen learns a widely applicable regeneration prior from off-the-shelf 3D datasets via self-supervised pretext tasks and augmentations, without additional annotations. We evaluate both the geometric consistency and fine-grained quality of MeshReGen, achieving state-of-the-art performance in controllable 3D generation across several tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。