MVS2D: Efficient Multiview Stereo via Attention-Driven 2D Convolutions

Deep learning has made significant impacts on multiview stereo systems. State-of-the-art approaches typically involve building a cost volume, followed by multiple 3D convolution operations to recover the input image's pixel-wise depth. While such end-to-end learning of plane-sweeping stereo advances public benchmarks' accuracy, they are typically very slow to compute. We present MVS2D, a highly efficient multi-view stereo algorithm that seamlessly integrates multi-view constraints into single-view net-works via an attention mechanism. Since MVS2D only builds on 2D convolutions, it is at least <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2\times faster$</tex> than all the notable counterparts. Moreover, our algorithm produces precise depth estimations and 3D reconstructions, achieving state-of-the-art results on challenging benchmarks ScanNet, SUN3D, RGBD, and the classical DTU dataset. our algorithm also outperforms all other algorithms in the setting of inexact camera poses. Our code is released at https://github.com/zhenpeiyang/MVS2D