no code implementations • ICCV 2023 • Mateusz Michalkiewicz, Masoud Faraki, Xiang Yu, Manmohan Chandraker, Mahsa Baktashmotlagh
Overfitting to the source domain is a common issue in gradient-based training of deep neural networks.
no code implementations • 11 Jun 2021 • Mateusz Michalkiewicz, Stavros Tsogkas, Sarah Parisot, Mahsa Baktashmotlagh, Anders Eriksson, Eugene Belilovsky
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.
no code implementations • 10 May 2020 • Mateusz Michalkiewicz, Eugene Belilovsky, Mahsa Baktashmotlagh, Anders Eriksson
Deep learning applied to the reconstruction of 3D shapes has seen growing interest.
1 code implementation • ECCV 2020 • Mateusz Michalkiewicz, Sarah Parisot, Stavros Tsogkas, Mahsa Baktashmotlagh, Anders Eriksson, Eugene Belilovsky
In this work we demonstrate experimentally that naive baselines do not apply when the goal is to learn to reconstruct novel objects using very few examples, and that in a \emph{few-shot} learning setting, the network must learn concepts that can be applied to new categories, avoiding rote memorization.
no code implementations • ICCV 2019 • Mateusz Michalkiewicz, Jhony K. Pontes, Dominic Jack, Mahsa Baktashmotlagh, Anders Eriksson
Implicit shape representations, such as Level Sets, provide a very elegant formulation for performing computations involving curves and surfaces.
no code implementations • 21 Jan 2019 • Mateusz Michalkiewicz, Jhony K. Pontes, Dominic Jack, Mahsa Baktashmotlagh, Anders Eriksson
This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"