English(EN) DepthART: Scaling Foundation Monocular Depth to Tiny Models

DepthART 模型将单目深度估计扩展到小型设备

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-21 04:00

研究人员开发了 DepthART，这是一种新的紧凑型单目深度估计模型，专为设备部署而设计。该模型通过采用抗偏差数据采样方案和相机条件微调协议，解决了小型模型的局限性。DepthART 在泛化能力和度量精度方面均表现出色，甚至接近大型模型的能力。 AI

影响通过提高资源受限硬件上的深度估计精度，从而实现更复杂的设备计算机视觉应用。

排序理由该集群包含一篇详细介绍新型计算机视觉模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新型计算机视觉模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 48 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Feng Xue, Wu Chen, Mingshuai Zhao, Guofeng Zhong, Anlong Ming, Haozhe Wang, Dianqiao Lei, Zhaowen Lin, Haiyang Zhang, Nicu Sebe · 2026-07-21 04:00

DepthART：将基础单目深度模型扩展到微型模型

arXiv:2607.17099v1 Announce Type: cross Abstract: Recent geometric foundation models (e.g., Metric3D, Depth Anything and UniDepth) have substantially improved monocular depth estimation (MDE) in both cross-scene generalization and metric-scale prediction, yet these gains have not…