English(EN) After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data

新的代理式工作流创建了多样化的阴影去除训练数据

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员开发了一种新的方法来创建图像中阴影去除的配对训练数据，解决了该领域长期存在的挑战。提出的离线代理式工作流结合了基于物理的生成、故障检测和迭代细化，构建了一个名为 AgenticShadow 的数据集。该数据集包含 17,138 个图像-掩码-目标三元组，涵盖各种场景类型，并在用于训练现有阴影去除模型时，在减少颜色差异和跨域误差方面显示出显著的改进。 AI

影响这个新数据集和工作流可以显著提高阴影去除模型在现实世界应用中的鲁棒性。

排序理由该集群描述了一种用于计算机视觉任务的新数据集和方法论，发表在一篇学术论文中。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 21 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一种用于计算机视觉任务的新数据集和方法论，发表在一篇学术论文中。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Shilin Hu, Jingyi Xu, Dimitris Samaras, Hieu Le · 2026-10-01 04:00

十年之后：通过Agentic训练数据将阴影移除引入现实世界

arXiv:2609.38607v1 Announce Type: cross Abstract: Shadow removal looks nearly solved on established benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data they rely on have barely changed in nearly a decade. The reason is simple: obtaini…

本文如何被排名

报道来源 [1]

十年之后：通过Agentic训练数据将阴影移除引入现实世界

相关实体

相关话题