We present a simple baseline for directly estimating the relative pose (rotation and translation, including scale) between two images. Deep methods have recently shown strong progress but often require complex or multi-stage architectures. We show that a handful of modifications can be applied to a Vision Transformer (ViT) to bring its computations close to the Eight-Point Algorithm. This inductive bias enables a simple method to be competitive in multiple settings, often substantially improving over the state of the art with strong performance gains in limited data regimes.

翻译：我们为直接估计两种图像之间的相对面貌(旋转和翻译,包括比例尺)提出了一个简单的基线。深层方法最近显示取得了很大进展,但往往需要复杂的或多阶段的结构。我们显示,可以对愿景变换器(VIT)进行一些修改,使其计算接近八点算法。这种推导偏差使得一种简单方法能够在多种环境中具有竞争力,往往比先进技术大为改进,在有限的数据制度中取得了很大的绩效收益。