Marcela Carvalho E. - Academia.edu (original) (raw)

Marcela Carvalho E.

Related Authors

Dr. Nafiz Imtiaz Bin Hamid

Derek  Abbott

Paul Tobin

Roshan Chitrakar

Lev Manovich

Lev Manovich

Graduate Center of the City University of New York

Mehmet Hakan Hocaoglu

Raghu Vamsi Potukuchi

Mohandas K P

Mayra Zahra

Devasena A.

Uploads

Papers by Marcela Carvalho E.

Research paper thumbnail of On Regression Losses for Deep Depth Estimation

2018 25th IEEE International Conference on Image Processing (ICIP), 2018

Depth estimation from a single monocular image has reached great performances thanks to recent wo... more Depth estimation from a single monocular image has reached great performances thanks to recent works based on deep networks. However, as various choices of losses, architectures and experimental conditions are proposed in the literature, it is difficult to establish their respective influence on the performances. In this paper we propose an in-depth study of various losses and experimental conditions for depth regression, on NYUv2 dataset. From this study we propose a new network for depth estimation combining an encoder-decoder architecture with an adversarial loss. This network reaches top ones state of the art on NUYv2 dataset while being simpler to train in a single phase.

Research paper thumbnail of On Regression Losses for Deep Depth Estimation

2018 25th IEEE International Conference on Image Processing (ICIP), 2018

Depth estimation from a single monocular image has reached great performances thanks to recent wo... more Depth estimation from a single monocular image has reached great performances thanks to recent works based on deep networks. However, as various choices of losses, architectures and experimental conditions are proposed in the literature, it is difficult to establish their respective influence on the performances. In this paper we propose an in-depth study of various losses and experimental conditions for depth regression, on NYUv2 dataset. From this study we propose a new network for depth estimation combining an encoder-decoder architecture with an adversarial loss. This network reaches top ones state of the art on NUYv2 dataset while being simpler to train in a single phase.

Log In