PointDiT: 面向单目几何估计的像素空间扩散

摘要

最先进的单图像三维重建方法通常依赖复杂的混合架构和损失函数，或者将几何信息压缩到潜在空间中，以利用预训练的潜在扩散模型。在这项工作中，我们表明这种架构开销和复杂的损失公式是不必要的。我们引入了一个极简的像素空间扩散Transformer，基于简单的ViT构建，直接操作原始三维点图块，并以预训练DINOv3的图像标记为条件。与现有的潜在扩散方法不同，我们从头开始训练扩散主干，消除了对点图分词器的需求。尽管设计简单，我们的方法超越了复杂的基于潜在扩散的模型，同时比混合替代方案显著更简洁。值得注意的是，它生成了更清晰的几何结构，并且在高度模糊区域（如透明物体）中更具鲁棒性。

English

State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage pre-trained latent diffusion models. In this work, we show that such architectural overhead and intricate loss formulations are unnecessary. We introduce a minimalist pixel-space Diffusion Transformer, built on a plain ViT, that operates directly on raw 3D point map patches and is conditioned on image tokens from a pre-trained DINOv3. Unlike existing latent diffusion approaches, we train our diffusion backbone entirely from scratch, eliminating the need for point map tokenizers. Despite its simplicity, our approach surpasses complex latent-based diffusion models while remaining significantly simpler than hybrid alternatives. Notably, it produces sharper geometric structure and is more robust in highly ambiguous regions, such as transparent objects.