Robustly reconstructing such a volumetric scene model with millions of unknown variables from registered scene images only is a highly non-convex and complex optimization problem.
We let a feature encoding network and image reconstruction network compete with each other, such that the feature encoder tries to impede the image reconstruction with its generated descriptors, while the reconstructor tries to recover the input image from the descriptors.
no code implementations • 9 May 2021 • Deeksha Dangwal, Vincent T. Lee, Hyo Jin Kim, Tianwei Shen, Meghan Cowan, Rajvi Shah, Caroline Trippel, Brandon Reagen, Timothy Sherwood, Vasileios Balntas, Armin Alaghi, Eddy Ilg
This poses a potential risk to user privacy.
We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons.
We show that our network, trained with pedestrian data from a headset, can produce statistically consistent measurement and uncertainty to be used as the update step in the filter, and the tightly-coupled system outperforms velocity integration approaches in position estimates, and AHRS attitude filter in orientation estimates.
Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception.
Future prediction is a fundamental principle of intelligence that helps plan actions and avoid possible dangers.
The latter can be used as proxy-ground-truth to train a network on real-world data and to adapt it to specific domains of interest.
Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.
Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology.
The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations.
We analyze the usage of optical flow for video super-resolution and find that common off-the-shelf image warping does not allow video super-resolution to benefit much from optical flow.
Our approach is suitable for both single and multiple object segmentation.
In this paper we formulate structure from motion as a learning problem.
Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
Optical flow estimation has not been among the tasks where CNNs were successful.