English(EN) Zero-Shot Depth from Defocus

新的FOSSA架构在零样本深度估计中将错误率降低了55.7%

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-30 04:00

研究人员开发了一种名为FOSSA的新型Transformer架构，用于从焦点堆栈估计密集度量深度图，即从离焦估计深度（DfD）。该新模型强调零样本泛化，旨在在未见过的、没有特定过拟合的数据集上表现良好。为此，创建了一个名为ZEDD的新基准，其场景数量和数据质量均显著高于以前的基准。FOSSA架构包含一个具有焦点距离嵌入的堆栈注意力层，用于高效的跨堆栈信息交换，实验表明，在ZEDD基准上，其错误率降低了高达55.7%。 AI

影响引入了一种新颖的深度估计架构和基准，有可能改善计算机视觉应用中的场景理解。

排序理由这是一篇详细介绍计算机视觉任务新模型架构和基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

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; 这是一篇详细介绍计算机视觉任务新模型架构和基准的研究论文。[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, other; 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: 72 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。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Yiming Zuo, Hongyu Wen, Venkat Subramanian, Patrick Chen, Karhan Kayan, Mario Bijelic, Felix Heide, Jia Deng · 2026-06-30 04:00

零样本离焦深度估计

arXiv:2603.26658v2 Announce Type: replace Abstract: Depth from Defocus (DfD) is the task of estimating a dense metric depth map from a focus stack. Unlike previous works overfitting to a certain dataset, this paper focuses on the challenging and practical setting of zero-shot gen…

本文如何被排名

报道来源 [1]

零样本离焦深度估计

相关实体

相关话题