We propose Differentiable Stereopsis, a multi-view stereo approach that
reconstructs shape and texture from few input views and noisy cameras. We pair
traditional stereopsis and modern differentiable rendering to build an
end-to-end model which predicts textured 3D meshes of objects with varying
topologies and shape. We frame stereopsis as an optimization problem and
simultaneously update shape and cameras via simple gradient descent. We run an
extensive quantitative analysis and compare to traditional multi-view stereo
techniques and state-of-the-art learning based methods. We show compelling
reconstructions on challenging real-world scenes and for an abundance of object
types with complex shape, topology and texture. Project webpage:
this https URL

本文提出了 Differentiable Stereopsis 方法，这是一种从少量输入视角和嘈杂相机中重建形状和纹理的多视角立体成像方法，其采用传统立体成像和现代可微渲染相结合的方法搭建了一个端到端的模型，通过简单的梯度下降同时更新形状和相机，并通过多量化分析将其与传统的多视角立体成像技术和最先进的基于学习的方法进行比较，在挑战实际场景中展示了有说服力的重建效果。