Search Results for author: Mikhail Romanov

Found 6 papers, 3 papers with code

Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data

no code implementations CVPR 2022 Nikolay Patakin, Mikhail Romanov, Anna Vorontsova, Mikhail Artemyev, Anton Konushin

On the contrary, we propose GP$^{2}$, General-Purpose and Geometry-Preserving training scheme, and show that conventional SVDE models can learn correct shifts themselves without any post-processing, benefiting from using stereo data even in the geometry-preserving setting.

3D Reconstruction Depth Estimation

Towards General Purpose Geometry-Preserving Single-View Depth Estimation

1 code implementation25 Sep 2020 Mikhail Romanov, Nikolay Patatkin, Anna Vorontsova, Sergey Nikolenko, Anton Konushin, Dmitry Senyushkin

Our work shows that a model trained on this data along with conventional datasets can gain accuracy while predicting correct scene geometry.

Monocular Depth Estimation Scene Understanding

Learning High-Resolution Domain-Specific Representations with a GAN Generator

1 code implementation18 Jun 2020 Danil Galeev, Konstantin Sofiiuk, Danila Rukhovich, Mikhail Romanov, Olga Barinova, Anton Konushin

Based on this finding, we propose LayerMatch scheme for approximating the representation of a GAN generator that can be used for unsupervised domain-specific pretraining.

Decoder Semi-Supervised Semantic Segmentation +1

Decoder Modulation for Indoor Depth Completion

1 code implementation18 May 2020 Dmitry Senushkin, Mikhail Romanov, Ilia Belikov, Anton Konushin, Nikolay Patakin

Our second contribution is a novel training strategy that allows us to train on a semi-dense sensor data when the ground truth depth map is not available.

Decoder Depth Completion +2

Cannot find the paper you are looking for? You can Submit a new open access paper.