Roman Bachmann
Roman Bachmann
PhD Student, EPFL
Verified email at
Cited by
Cited by
Multimae: Multi-modal multi-task masked autoencoders
R Bachmann, D Mizrahi, A Atanov, A Zamir
Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel …, 2022
Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans
A Eftekhar, A Sax, J Malik, A Zamir
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
Clipasso: Semantically-aware object sketching
Y Vinker, E Pajouheshgar, JY Bo, RC Bachmann, AH Bermano, ...
ACM Transactions on Graphics (TOG) 41 (4), 1-11, 2022
Training Binary Neural Networks using the Bayesian Learning Rule
X Meng, R Bachmann, ME Khan
2020 International Conference on Machine Learning (ICML), 2020
Motion Capture from Pan-Tilt Cameras with Unknown Orientation
R Bachmann, J Spörri, P Fua, H Rhodin
2019 International Conference on 3D Vision (3DV), 308-317, 2019
4M: Massively Multimodal Masked Modeling
D Mizrahi, R Bachmann, OF Kar, T Yeo, M Gao, A Dehghan, A Zamir
Thirty-seventh Conference on Neural Information Processing Systems, 2023
Modality-invariant Visual Odometry for Embodied Vision
M Memmel, R Bachmann, A Zamir
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
Global Motion Estimation from Pan-Tilt Cameras
R Bachmann, H Rhodin, P Fua
2019 Central European Seminar on Computer Graphics (CESCG) (non-peer-reviewed), 2019
Automatic 3D motion capture in alpine skiing using deep learning and computer vision
R Bachmann, H Rhodin, J Spörri, P Fua
8th Int. Congress on Science and Skiing (ICSS) (non-peer-reviewed), 14, 2019
The system can't perform the operation now. Try again later.
Articles 1–9