Mikhail Romanov — accepted AI-conference papers

2021

Decoder Modulation for Indoor Depth Completion

Dmitry Senushkin, Mikhail Romanov, Ilia Belikov, Nikolay Patakin, Anton Konushin

IROS 2021poster

Depth completion recovers a dense depth map from sensor measurements. Current methods are mostly tailored for very sparse depth measurements from LiDARs in outdoor settings, while for indoor scenes Time-of-Flight (ToF) or structured light sensors are mostly used. These sensors provide semi-dense map…

Cited by 52 Source ↗Scholar ↗

2019

Double Refinement Network for Efficient Monocular Depth Estimation

Nikita Durasov, Mikhail Romanov, Valeriya Bubnova, Pavel Bogomolov, Anton Konushin

IROS 2019poster

Monocular depth estimation is the task of obtaining a measure of distance for each pixel using a single image. It is an important problem in computer vision and is usually solved using neural networks. Though recent works in this area have shown significant improvement in accuracy, the state-of-the-…

Cited by 15 Source ↗Scholar ↗