轻量级框架实现零样本单目深度估计，精度更高且参数减少85%以上
AnyDepth: Depth Estimation Made Easy
- 用DINOv3提取特征，设计紧凑Transformer解码器SDT
- 相比DPT参数减少85%-89%，在五个基准上精度更优
- 基于质量筛选有害样本，提升训练效率与泛化能力
单目深度估计旨在从2D图像中恢复3D场景的深度信息。近期工作虽取得进展，但依赖大规模数据集和复杂解码器，限制了效率与泛化能力。本文提出一种轻量级、数据驱动的零样本单目深度估计框架。首先采用DINOv3作为视觉编码器获取高质量稠密特征；其次，针对DPT复杂结构的缺陷，设计了简洁深度变换器（SDT），通过单路径特征融合与上采样降低跨尺度特征融合的计算开销，相较DPT参数减少约85%-89%，同时提升精度。此外，提出基于质量的过滤策略，剔除有害样本，在减小数据集规模的同时提高整体训练质量。在五个基准上的大量实验表明，该框架在精度上超越DPT。本工作强调了模型设计与数据质量平衡对高效、可泛化零样本深度估计的重要性。
原文摘要 · Abstract (English)
Monocular depth estimation aims to recover the depth information of 3D scenes from 2D images. Recent work has made significant progress, but its reliance on large-scale datasets and complex decoders has limited its efficiency and generalization ability. In this paper, we propose a lightweight and data-centric framework for zero-shot monocular depth estimation. We first adopt DINOv3 as the visual encoder to obtain high-quality dense features. Secondly, to address the inherent drawbacks of the complex structure of the DPT, we design the Simple Depth Transformer (SDT), a compact transformer-based decoder. Compared to the DPT, it uses a single-path feature fusion and upsampling process to reduce the computational overhead of cross-scale feature fusion, achieving higher accuracy while reducing the number of parameters by approximately 85%-89%. Furthermore, we propose a quality-based filtering strategy to filter out harmful samples, thereby reducing dataset size while improving overall training quality. Extensive experiments on five benchmarks demonstrate that our framework surpasses the DPT in accuracy. This work highlights the importance of balancing model design and data quality for achieving efficient and generalizable zero-shot depth estimation. Code: https://github.com/AIGeeksGroup/AnyDepth. Website: https://aigeeksgroup.github.io/AnyDepth.
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。