196 papers with code • 6 benchmarks • 24 datasets
Reconstructing 4D vehicular activity (3D space and time) from cameras is useful for autonomous vehicles, commuters and local authorities to plan for smarter and safer cities.
This paper introduces an approach for multi-human 3D pose estimation and tracking based on calibrated multi-view.
Ranked #2 on 3D Multi-Person Pose Estimation on Campus
The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space.
Ground Penetrating Radar (GPR) is an effective non-destructive evaluation (NDE) device for inspecting and surveying subsurface objects (i. e., rebars, utility pipes) in complex environments.
It is a particular variation of multibody structure from motion, which specializes to two objects only.
In this work, an Information Fusion framework is proposed to seamlessly fuse heterogeneous components in a Digital Twin framework from the variety of technologies involved.
We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images.
We consider three classical cases--3-point absolute pose, 5-point relative pose, and 4-point homography estimation for calibrated cameras--where the decomposition and symmetries may be naturally understood in terms of the Galois/monodromy group.