NBS：无偏立体匹配

中文摘要 AI 辅助

立体重建是计算机视觉领域中少数仍存在以下情况的任务之一：所有最先进的方法都采用了大量的架构归纳偏置。尽管已有研究表明该任务可通过通用方法解决，但人们普遍认为，立体匹配中的归纳偏置对于获得高质量结果和计算效率都是绝对必要的。我们对这一范式提出了挑战。在本文中，我们证明了完全缺乏架构归纳偏置的模型既能达到最先进的准确率，又能实现更优的运行时效率，该模型仅依赖于简单的端到端Vision Transformer。通过在大规模合成数据集上进行训练，我们表明纯数据驱动的学习可以超越显式设计的几何结构。本研究证明，显式归纳偏置不再是立体匹配的先决条件，最终为3D重建领域的持续改进解锁了真正的缩放定律。

英文摘要

Stereo reconstruction is one of the last remaining Computer Vision tasks where all state-of-the-art methods employ a heavy architectural inductive bias. Even though it has been demonstrated that the task can be solved using general-purpose methods, it is widely believed that inductive biases in stereo are strictly necessary for both high-quality results and computational efficiency. We challenge this paradigm. In this paper, we demonstrate that both state-of-the-art accuracy and superior runtime efficiency are achievable with a model completely devoid of architectural inductive biases, relying instead on a simple, end-to-end Vision Transformer. By training on massive synthetic datasets, we show that pure data-driven learning can surpass explicitly engineered geometry. This work proves that explicit inductive biases are no longer a prerequisite for stereo matching, ultimately unlocking true scaling laws for continuous improvement in 3D reconstruction.

发表机构

• Intrinsic (Google)（Intrinsic（谷歌））
• Texas A&M University（德克萨斯农工大学）

机构由 AI 辅助整理，请以论文原文为准。