no code implementations • ECCV 2020 • Bin Cheng, Inderjot Singh Saggu, Raunak Shah, Gaurav Bansal, Dinesh Bharadia
In order to learn such a scalable depth estimation model, we require a ton of data and labels which are targeted towards specific use-cases.
no code implementations • 28 Jul 2020 • Bin Cheng, Inderjot Singh Saggu, Raunak Shah, Gaurav Bansal, Dinesh Bharadia
We present $S^3$Net, a self-supervised framework which combines these complementary features: we use synthetic and real-world images for training while exploiting geometric, temporal, as well as semantic constraints.
2 code implementations • CVPR 2019 • Yue Meng, Yongxi Lu, Aman Raj, Samuel Sunarjo, Rui Guo, Tara Javidi, Gaurav Bansal, Dinesh Bharadia
SIGNet is shown to improve upon the state-of-the-art unsupervised learning for depth prediction by 30% (in squared relative error).
Ranked #62 on Monocular Depth Estimation on KITTI Eigen split