1 code implementation • 4 Aug 2018 • Denis Tome, Matteo Toso, Lourdes Agapito, Chris Russell
We propose a CNN-based approach for multi-camera markerless motion capture of the human body.
Ranked #201 on 3D Human Pose Estimation on Human3.6M
1 code implementation • NeurIPS 2019 • Chris Russell, Matteo Toso, Neill Campbell
We present a new technique for the learning of continuous energy functions that we refer to as Wibergian Learning.
1 code implementation • 19 Jul 2022 • Matteo Taiana, Matteo Toso, Stuart James, Alessio Del Bue
The estimation of the camera poses associated with a set of images commonly relies on feature matches between the images.
1 code implementation • 13 Apr 2023 • Matteo Toso, Matteo Taiana, Stuart James, Alessio Del Bue
Efficient visual localization is crucial to many applications, such as large-scale deployment of autonomous agents and augmented reality.
no code implementations • 13 Mar 2024 • Matteo Taiana, Matteo Toso, Stuart James, Alessio Del Bue
Robustly estimating camera poses from a set of images is a fundamental task which remains challenging for differentiable methods, especially in the case of small and sparse camera pose graphs.
no code implementations • 19 Apr 2024 • Myrna C. Silva, Mahtab Dahaghin, Matteo Toso, Alessio Del Bue
Recent works in novel-view synthesis have shown how to model the appearance of a scene via a cloud of 3D Gaussians, and how to generate accurate images from a given viewpoint by projecting on it the Gaussians before $\alpha$ blending their color.