How Good MVSNets Are at Depth Fusion
This work addresses the problem of improving multi-view stereo reconstruction quality for computer vision researchers by exploring the utility of readily available, albeit low-quality, sensor depth data.
This paper investigates the impact of incorporating low-quality sensor depth as an additional input to deep multi-view stereo (MVS) methods. By modifying two state-of-the-art deep MVS techniques, the authors demonstrate that this additional input can enhance the quality of the resulting stereo reconstruction.
We study the effects of the additional input to deep multi-view stereo methods in the form of low-quality sensor depth. We modify two state-of-the-art deep multi-view stereo methods for using with the input depth. We show that the additional input depth may improve the quality of deep multi-view stereo.