Suivre
Edward James Smith
Edward James Smith
Borealis AI, McGill University
Adresse e-mail validée de mail.mcgill.ca - Page d'accueil
Titre
Citée par
Citée par
Année
Learning to predict 3d objects with an interpolation-based differentiable renderer
W Chen, H Ling, J Gao, E Smith, J Lehtinen, A Jacobson, S Fidler
Advances in neural information processing systems 32, 2019
3582019
Improved adversarial systems for 3d object generation and reconstruction
EJ Smith, D Meger
Conference on Robot Learning, 87-96, 2017
1842017
Geometrics: Exploiting geometric structure for graph-encoded objects
EJ Smith, S Fujimoto, A Romero, D Meger
arXiv preprint arXiv:1901.11461, 2019
1052019
Kaolin: A pytorch library for accelerating 3d deep learning research
KM Jatavallabhula, E Smith, JF Lafleche, CF Tsang, A Rozantsev, ...
arXiv preprint arXiv:1911.05063, 2019
77*2019
Frame averaging for invariant and equivariant network design
O Puny, M Atzmon, H Ben-Hamu, I Misra, A Grover, EJ Smith, Y Lipman
arXiv preprint arXiv:2110.03336, 2021
752021
Multi-view silhouette and depth decomposition for high resolution 3d object representation
E Smith, S Fujimoto, D Meger
Advances in Neural Information Processing Systems 31, 2018
512018
3d shape reconstruction from vision and touch
E Smith, R Calandra, A Romero, G Gkioxari, D Meger, J Malik, M Drozdzal
Advances in Neural Information Processing Systems 33, 14193-14206, 2020
412020
Active 3D shape reconstruction from vision and touch
E Smith, D Meger, L Pineda, R Calandra, J Malik, A Romero Soriano, ...
Advances in Neural Information Processing Systems 34, 16064-16078, 2021
222021
For sale: State-action representation learning for deep reinforcement learning
S Fujimoto, WD Chang, E Smith, SS Gu, D Precup, D Meger
Advances in Neural Information Processing Systems 36, 2024
112024
Uncertainty-Driven Active Vision for Implicit Scene Reconstruction
EJ Smith, M Drozdzal, D Nowrouzezahrai, D Meger, A Romero-Soriano
arXiv preprint arXiv:2210.00978, 2022
52022
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–10