让3D重建模型在测试时自我优化，无需真实标签
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself
- 通过多视角一致性设计自监督任务，让模型在测试时自我修正
- 在4个数据集上平均提升相机位姿精度3.73%、点云预测2.88%
- 仅需单卡2分钟即可完成轻量级微调，适合部署到实际场景
前馈式3D重建模型效率高但缺乏适应性：训练后无法根据测试场景调整，常在遮挡、反光和模糊线索下产生错误。为此，我们提出Free Geometry框架，使这类模型能在无3D真值的情况下于测试时自我演化。核心思想是：接收更多视角时，模型输出更可靠且视图一致。给定测试序列，我们掩码部分帧构造自监督任务，强制完整与部分观测间的跨视角特征一致性，同时保留被遮挡帧的成对关系。该自监督机制支持快速轻量级微调（单卡<2分钟/数据集），显著提升现有基础模型（如Depth Anything 3、VGGT）在4个基准数据集上的表现，平均提升相机位姿精度3.73%、点云预测2.88%。代码已开源。
原文摘要 · Abstract (English)
Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test scene. As a result, visually plausible reconstructions often contain errors, particularly under occlusions, specularities, and ambiguous cues. To address this, we introduce Free Geometry, a framework that enables feed-forward 3D reconstruction models to self-evolve at test time without any 3D ground truth. Our key insight is that, when the model receives more views, it produces more reliable and view-consistent reconstructions. Leveraging this property, given a testing sequence, we mask a subset of frames to construct a self-supervised task. Free Geometry enforces cross-view feature consistency between representations from full and partial observations, while maintaining the pairwise relations implied by the held-out frames. This self-supervision allows for fast recalibration via lightweight LoRA updates, taking less than 2 minutes per dataset on a single GPU. Our approach consistently improves state-of-the-art foundation models, including Depth Anything 3 and VGGT, across 4 benchmark datasets, yielding an average improvement of 3.73% in camera pose accuracy and 2.88% in point map prediction. Code is available at https://github.com/hiteacherIamhumble/Free-Geometry .
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。