E-RayZer：自监督三维重建作为空间视觉预训练
E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training
将自监督三维重建作为空间视觉预训练任务，直接学习几何感知表征，可替代DINOv3等2D预训练模型用于姿态估计等3D下游任务。
原文依据 Self-supervised pre-training has driven rapid progress in foundation models for language, 2D images, and video, yet remains largely unexplored for learning 3D-aware representations from multi-view images.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自监督预训练推动了语言、二维图像和视频基础模型的快速发展，然而从多视图图像中学习三维感知表征在很大程度上仍未被探索。本文提出E-RayZer，一种自监督三维视觉模型，可直接从无标注图像中学习具有几何基础的表示。与RayZer等通过隐空间视图合成间接推断三维的先验自监督方法不同，E-RayZer直接在三维空间中操作，利用显式几何进行自监督三维重建。该公式消除了捷径解，并产生三维感知的表示。为确保收敛性和可扩展性，我们引入了一种细粒度学习课程，从易到难组织训练样本，并在无任何监督的情况下协调异构数据源。实验表明，E-RayZer在姿态估计上显著优于RayZer，并匹配或有时超越VGGT等全监督重建模型。此外，其学习到的表示在三维下游任务上优于领先的视觉预训练模型（如DINOv3、CroCo v2、VideoMAE V2和RayZer），确立了E-RayZer作为空间视觉预训练的有前景范式。
英文原文摘要 1290 字符
Self-supervised pre-training has driven rapid progress in foundation models for language, 2D images, and video, yet remains largely unexplored for learning 3D-aware representations from multi-view images. In this paper, we present E-RayZer, a self-supervised 3D vision model that learns geometrically grounded representations directly from unlabeled images. Unlike prior self-supervised methods such as RayZer, which infer 3D indirectly through latent-space view synthesis, E-RayZer operates directly in 3D space, performing self-supervised 3D reconstruction with Explicit geometry. This formulation eliminates shortcut solutions and yields representations that are 3D-aware. To ensure convergence and scalability, we introduce a fine-grained learning curriculum that organizes training from easy to hard samples and harmonizes heterogeneous data sources without any supervision. Experiments show that E-RayZer significantly outperforms RayZer on pose estimation and matches or sometimes surpasses fully supervised reconstruction models such as VGGT. Furthermore, its learned representations outperform leading visual pre-training models (e.g., DINOv3, CroCo v2, VideoMAE V2, and RayZer) on 3D downstream tasks, establishing E-RayZer as a promising paradigm for spatial visual pre-training.