用扩散模型生成先验，高效实现高精度单目深度估计
FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation
- 将扩散生成器转换为前馈结构，利用扩散先验提升深度估计
- 在多个基准上实现更精确、更稳定的深度图，细节丰富
- 适合需要高精度深度图的3D重建与自动驾驶场景
单目深度估计（MDE）是3D视觉的基础任务，广泛应用于3D场景重建、自动驾驶和AI内容生成。然而，由于真实世界标注数据有限，以及合成数据与真实数据之间的分布差异，实现鲁棒且泛化能力强的MDE仍具挑战。现有方法在真实测试数据上常表现出效率低、精度下降、细节不足等问题。为此，本文提出FiffDepth，一种高效的MDE方法。其核心在于利用扩散模型的生成先验，将基于扩散的图像生成器转化为前馈架构，用于精细化深度估计。FiffDepth保留了关键生成特性，并融合了DINOv2等模型的强大泛化能力。在多个基准测试中，该方法在精度、稳定性和细粒度细节方面均显著优于现有最先进方法。
原文摘要 · Abstract (English)
Monocular Depth Estimation (MDE) is a fundamental 3D vision problem with numerous applications such as 3D scene reconstruction, autonomous navigation, and AI content creation. However, robust and generalizable MDE remains challenging due to limited real-world labeled data and distribution gaps between synthetic datasets and real data. Existing methods often struggle with real-world test data with low efficiency, reduced accuracy, and lack of detail. To address these issues, we propose an efficient MDE approach named FiffDepth. The key feature of FiffDepth is its use of diffusion priors. It transforms diffusion-based image generators into a feed-forward architecture for detailed depth estimation. FiffDepth preserves key generative features and integrates the strong generalization capabilities of models like DINOv2. Through benchmark evaluations, we demonstrate that FiffDepth achieves exceptional accuracy, stability, and fine-grained detail, offering significant improvements in MDE performance against state-of-the-art MDE approaches. The paper's source code is available here: https://yunpeng1998.github.io/FiffDepth/
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。