arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.26488cs.CVcs.LG
收藏

从动态3D场景中提取像素特征的线性上下文学习器

Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners

Google(谷歌);TU Munich(慕尼黑工业大学);Munich Center for Machine Learning(慕尼黑机器学习中心)

Nikita Araslanov, Martin Sundermeyer, Hidenobu Matsuki, David Joseph Tan, Federico Tombari

AI总结:

本文提出LILA框架,通过线性上下文学习从视频中提取精确像素特征,解决动态场景中像素级表示问题,应用于视频目标分割、表面法线估计和语义分割等任务。

摘要:

视觉模型最激动人心的应用之一是像素级推理。尽管存在大量视觉基础模型,但我们仍缺乏能够有效嵌入视觉场景像素级空间-时间属性的表示方法。现有框架要么在图像基础上训练 pretext 任务,无法考虑动态元素,要么在视频序列上训练进行动作级推理,无法扩展到密集像素级预测。我们提出一个从视频中学习像素级特征描述符的框架LILA。我们训练框架的核心元素是线性上下文学习。LILA利用空间-时间提示图——通过现成网络估计的深度和运动信息。尽管这些提示具有噪声性质,LILA仍能有效在未经过滤的视频数据集上训练,以时间一致的方式嵌入语义和几何属性。我们展示了在多样化的视觉任务中,所学表示的有说服力的实证收益:视频目标分割、表面法线估计和语义分割。

英文摘要:

One of the most exciting applications of vision models involve pixel-level reasoning. Despite the abundance of vision foundation models, we still lack representations that effectively embed spatio-temporal properties of visual scenes at the pixel level. Existing frameworks either train on image-based pretext tasks, which do not account for dynamic elements, or on video sequences for action-level reasoning, which does not scale to dense pixel-level prediction. We present a framework that learns pixel-accurate feature descriptors from videos, LILA. The core element of our training framework is linear in-context learning. LILA leverages spatio-temporal cue maps -- depth and motion -- estimated with off-the-shelf networks. Despite the noisy nature of those cues, LILA trains effectively on uncurated video datasets, embedding semantic and geometric properties in a temporally consistent manner. We demonstrate compelling empirical benefits of the learned representation across a diverse suite of vision tasks: video object segmentation, surface normal estimation and semantic segmentation.

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。

↑