提升单目深度估计在复杂场景下的泛化能力，关键突破在仿射不变预测。
The Fourth Monocular Depth Estimation Challenge
- 采用双自由度最小二乘对齐评估新协议，支持仿射不变预测。
- 挑战胜者3D F-Score达23.05%，较上届提升0.47个百分点。
- 适合关注零样本泛化与鲁棒深度估计的研究者参考。
本文呈现第四届单目深度估计挑战赛（MDEC）的结果，聚焦于在SYNS-Patches基准上的零样本泛化能力，该数据集涵盖自然与室内场景的高难度环境。本版挑战修订了评估协议，采用双自由度最小二乘对齐以支持视差与仿射不变预测。同时更新了基线方法，引入主流现成模型Depth Anything v2和Marigold。共收到24份提交，均在测试集上优于基线；其中10份附有方法报告，多数领先方法依赖仿射不变预测。冠军方案将3D F-Score提升至23.05%，相较上届最佳结果22.58%显著提高。
原文摘要 · Abstract (English)
This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. In this edition, we revised the evaluation protocol to use least-squares alignment with two degrees of freedom to support disparity and affine-invariant predictions. We also revised the baselines and included popular off-the-shelf methods: Depth Anything v2 and Marigold. The challenge received a total of 24 submissions that outperformed the baselines on the test set; 10 of these included a report describing their approach, with most leading methods relying on affine-invariant predictions. The challenge winners improved the 3D F-Score over the previous edition's best result, raising it from 22.58% to 23.05%.
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。