AI 中文总结
该研究针对单目深度估计中受水平先验（长尾方向偏差）导致的相机翻滚鲁棒性差问题，提出训练时监督策略ID-Constraint，经多基准数据集实验验证了方法的有效性。
AI 中文摘要
尽管单目深度估计近期取得了进展，但最先进的深度基础模型仍存在鲁棒性问题，尤其是轻微的相机翻滚就会导致深度估计大幅下降。我们将此问题归因于此前被忽视的“水平先验”现象，它是长尾分布偏差的表现：由于人类视觉偏好和摄影习惯，大多数训练图像以近似水平方向拍摄。虽然重新平衡数据增强、水平调平等直观补救措施能提供部分改进，但无法完全解决问题。本文提出训练时监督策略“不变深度约束（ID-Constraint）”，通过微调深度骨干网络并联合正则化一系列几何与空间推理任务，提升抗翻滚能力。这些辅助目标促使骨干学习旋转稳定、与深度相关的表征，且辅助预测头在训练后会被丢弃，保留原推理架构不变。在四个翻滚设置下的五个基准数据集上开展的大量实验，验证了所提方法的有效性。
英文摘要
Despite recent advances in Monocular Depth Estimation, state-of-the-art depth foundation models remain vulnerable to robustness issues. Particularly, even slight camera rolls can result in substantial degradation in depth estimations. We attribute this problem to a previously overlooked phenomenon, termed the Horizontal Prior, which is a manifestation of long-tailed distribution bias: most training images are captured in approximately horizontal orientations due to human visual preferences and photographic habits. While intuitive remedies such as re-balanced data augmentation and horizon leveling provide partial improvements, they fail to fully address the issue. In this paper, we introduce Invariant Depth Constraint (ID-Constraint), a training-time supervision strategy that improves roll robustness by fine-tuning and jointly regularizing the depth backbone with a series of geometric and spatial reasoning tasks. These auxiliary objectives encourage the backbone to learn rotation-stable, depth-relevant representations, while the auxiliary prediction heads are discarded after training, leaving the original inference architecture unchanged. Extensive experiments on five benchmark datasets across four roll settings demonstrate the effectiveness of the proposed method.
CommentsThe code is publicly available on GitHub: https://github.com/KaihuaTang/Horizontal-Prior
