1.4k citations · 1.9k across the 39 of their papers we have counts for
3 papers · 1 filter
You Only Train Once
Christos Sakaridis
The title of this paper is perhaps an overclaim. Of course, the process of creating and optimizing a learned model inevitably involves multiple training runs which potentially feat…
Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion
Kamil Adamczewski, Christos Sakaridis, Vaishakh Patil +1
Lidar is a vital sensor for estimating the depth of a scene. Typical spinning lidars emit pulses arranged in several horizontal lines and the monetary cost of the sensor increases…
TT-NF: Tensor Train Neural Fields
Anton Obukhov, Mikhail Usvyatsov, Christos Sakaridis +2
Learning neural fields has been an active topic in deep learning research, focusing, among other issues, on finding more compact and easy-to-fit representations. In this paper, we…