只需一张图，就能生成可编辑的3D衣服，效果更真实连贯。
GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing
- 分步预测深度并扭曲图像，逐步生成新视角。
- 多视角扩散模型修复遮挡区域，保持整体一致性。
- 适合服装设计新手，也能精细还原衣物细节。
我们提出GarmentCrafter，一种让非专业人士仅凭单张图像即可创建和编辑3D服装的新方法。尽管图像生成技术已推动2D服装设计发展，但3D服装的构建与修改对普通用户仍具挑战。现有单视图3D重建方法依赖预训练生成模型，在参考图像和相机位姿条件下合成新视角，却缺乏跨视角一致性，难以捕捉不同视角间的内在关系。本文通过渐进式深度预测与图像扭曲来逼近新视角，随后训练多视角扩散模型，基于不断演化的相机位姿完成遮挡及未知区域的补全。通过联合推断RGB与深度信息，GarmentCrafter强化了视角间的一致性，精确重建几何结构与细微特征。大量实验表明，该方法在视觉保真度和跨视角一致性上优于当前最先进的单视图3D服装重建方法。
原文摘要 · Abstract (English)
We introduce GarmentCrafter, a new approach that enables non-professional users to create and modify 3D garments from a single-view image. While recent advances in image generation have facilitated 2D garment design, creating and editing 3D garments remains challenging for non-professional users. Existing methods for single-view 3D reconstruction often rely on pre-trained generative models to synthesize novel views conditioning on the reference image and camera pose, yet they lack cross-view consistency, failing to capture the internal relationships across different views. In this paper, we tackle this challenge through progressive depth prediction and image warping to approximate novel views. Subsequently, we train a multi-view diffusion model to complete occluded and unknown clothing regions, informed by the evolving camera pose. By jointly inferring RGB and depth, GarmentCrafter enforces inter-view coherence and reconstructs precise geometries and fine details. Extensive experiments demonstrate that our method achieves superior visual fidelity and inter-view coherence compared to state-of-the-art single-view 3D garment reconstruction methods.
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。