arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.09896cs.CVcs.LGeess.IV
收藏

GRIN:基于像素级扩散的零样本度量深度估计

GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion

Toyota Research Institute (TRI)(丰田研究所(TRI))

Vitor Guizilini, Pavel Tokmakov, Achal Dave, Rares Ambrus

AI总结:

针对现有扩散深度模型依赖稠密真值的问题,提出可处理稀疏非结构化数据的GRIN扩散模型,通过带3D几何位置编码的图像特征全局局部条件引导像素级深度生成,从零训练也在8个数据集上刷新零样本度量单目深度估计SOTA。

摘要:

从单张图像进行3D重建是计算机视觉领域的一个长期存在的问题。基于学习的方法通过利用规模不断扩大的标注和未标注数据集来解决其固有的尺度模糊问题,以生成能够跨域产生准确预测的几何先验。因此,当前最先进的方法在零样本相对深度和度量深度估计中展现出了出色的性能。近年来,扩散模型在其学习到的表征中展现出了显著的可扩展性和泛化特性。然而,由于这些模型重新利用了原本为图像生成设计的工具,它们只能在稠密真值数据上运行,而大多数深度标签(尤其是真实场景中的深度标签)并不具备这样的稠密真值。在本文中,我们提出了GRIN,这是一种高效的扩散模型,旨在处理稀疏非结构化训练数据。我们使用带有3D几何位置编码的图像特征,从全局和局部两个层面为扩散过程提供条件,生成像素级的深度预测。通过在8个室内和室外数据集上开展的综合实验,我们表明,即使是从头开始训练,GRIN也在零样本度量单目深度估计任务上树立了新的最先进水平。

英文摘要:

3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors capable of generating accurate predictions across domains. As a result, state of the art approaches show impressive performance in zero-shot relative and metric depth estimation. Recently, diffusion models have exhibited remarkable scalability and generalizable properties in their learned representations. However, because these models repurpose tools originally designed for image generation, they can only operate on dense ground-truth, which is not available for most depth labels, especially in real-world settings. In this paper we present GRIN, an efficient diffusion model designed to ingest sparse unstructured training data. We use image features with 3D geometric positional encodings to condition the diffusion process both globally and locally, generating depth predictions at a pixel-level. With comprehensive experiments across eight indoor and outdoor datasets, we show that GRIN establishes a new state of the art in zero-shot metric monocular depth estimation even when trained from scratch.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑