Robust Consistent Video Depth Estimation
This work provides a robust solution for accurate depth and pose estimation from noisy monocular video, which is beneficial for applications like AR/VR and robotics, representing an incremental improvement over existing methods.
This paper introduces an algorithm for estimating consistent dense depth maps and camera poses from monocular video. It combines a learning-based depth prior with geometric optimization, outperforming state-of-the-art methods on the Sintel benchmark for both depth and pose estimations.
We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video. We integrate a learning-based depth prior, in the form of a convolutional neural network trained for single-image depth estimation, with geometric optimization, to estimate a smooth camera trajectory as well as detailed and stable depth reconstruction. Our algorithm combines two complementary techniques: (1) flexible deformation-splines for low-frequency large-scale alignment and (2) geometry-aware depth filtering for high-frequency alignment of fine depth details. In contrast to prior approaches, our method does not require camera poses as input and achieves robust reconstruction for challenging hand-held cell phone captures containing a significant amount of noise, shake, motion blur, and rolling shutter deformations. Our method quantitatively outperforms state-of-the-arts on the Sintel benchmark for both depth and pose estimations and attains favorable qualitative results across diverse wild datasets.