SYSTEMS AND METHODS FOR DEPTH SYNTHESIS WITH TRANSFORMER ARCHITECTURES V Guizilini, I Vasiljevic, AD Gaidon, G Shakhnarovich, M Walter, J Fang, ... US Patent App. 18/156,958, 2024 | | 2024 |
Scale-aware depth estimation using multi-camera projection loss V Guizilini, RA Ambrus, AD Gaidon, I Vasiljevic, G Shakhnarovich US Patent 12,033,341, 2024 | 2 | 2024 |
DataComp-LM: In search of the next generation of training sets for language models J Li, A Fang, G Smyrnis, M Ivgi, M Jordan, S Gadre, H Bansal, E Guha, ... arXiv preprint arXiv:2406.11794, 2024 | 2 | 2024 |
Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometry T Kanai, I Vasiljevic, V Guizilini, K Shintani arXiv preprint arXiv:2406.00929, 2024 | | 2024 |
Radiant and volumetric latent space encoding for volumetric rendering V Guizilini, RA Ambrus, J Fang, S Zakharov, V Sitzmann, I Vasiljevic, ... US Patent App. 18/364,946, 2024 | | 2024 |
Cross-attention decoding for volumetric rendering V Guizilini, RA Ambrus, J Fang, S Zakharov, V Sitzmann, I Vasiljevic, ... US Patent App. 18/364,783, 2024 | | 2024 |
Shared latent spaces for volumetric rendering V Guizilini, RA Ambrus, J Fang, S Zakharov, V Sitzmann, I Vasiljevic, ... US Patent App. 18/364,922, 2024 | | 2024 |
Linearizing Large Language Models J Mercat, I Vasiljevic, S Keh, K Arora, A Dave, A Gaidon, T Kollar arXiv preprint arXiv:2405.06640, 2024 | 1 | 2024 |
Self-supervised depth for volumetric rendering regularization V Guizilini, RA Ambrus, J Fang, S Zakharov, V Sitzmann, I Vasiljevic, ... US Patent App. 18/364,853, 2024 | | 2024 |
Transcrib3D: 3D Referring Expression Resolution through Large Language Models J Fang, X Tan, S Lin, I Vasiljevic, V Guizilini, H Mei, R Ambrus, ... arXiv preprint arXiv:2404.19221, 2024 | | 2024 |
Language models scale reliably with over-training and on downstream tasks SY Gadre, G Smyrnis, V Shankar, S Gururangan, M Wortsman, R Shao, ... arXiv preprint arXiv:2403.08540, 2024 | 10 | 2024 |
Language models scale reliably with over-training and on downstream tasks S Yitzhak Gadre, G Smyrnis, V Shankar, S Gururangan, M Wortsman, ... arXiv e-prints, arXiv: 2403.08540, 2024 | | 2024 |
Geometric 3d augmentations for transformer architectures V Guizilini, I Vasiljevic, AD Gaidon, J Fang, G Shakhnarovich, MR Walter, ... US Patent App. 18/110,421, 2024 | | 2024 |
Self-occlusion masks to improve self-supervised monocular depth estimation in multi-camera settings V Guizilini, RA Ambrus, AD Gaidon, I Vasiljevic, G Shakhnarovich US Patent 11,875,521, 2024 | 1 | 2024 |
System and method to improve multi-camera monocular depth estimation using pose averaging V Guizilini, RA Ambrus, AD Gaidon, I Vasiljevic, G Shakhnarovich US Patent App. 18/344,750, 2023 | | 2023 |
Robust Self-Supervised Extrinsic Self-Calibration T Kanai, I Vasiljevic, V Guizilini, A Gaidon, R Ambrus 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2023 | 2 | 2023 |
System and method to improve multi-camera monocular depth estimation using pose averaging V Guizilini, RA Ambrus, AD Gaidon, I Vasiljevic, G Shakhnarovich US Patent 11,727,589, 2023 | 1 | 2023 |
Systems and methods for multi-camera modeling with neural camera networks V Guizilini, I Vasiljevic, RA Ambrus, A Gaidon US Patent 11,704,822, 2023 | | 2023 |
Camera agnostic depth network V Guizilini, S Pillai, AD Gaidon, RA Ambrus, I Vasiljevic US Patent 11,704,821, 2023 | | 2023 |
Shared median-scaling metric for multi-camera self-supervised depth evaluation V Guizilini, RA Ambrus, AD Gaidon, I Vasiljevic, G Shakhnarovich US Patent 11,688,090, 2023 | 2 | 2023 |