METHODS FOR RECONSTRUCTION OF DEPTH MAP AND ELECTRONIC COMPUTER DEVICE FOR THEIR IMPLEMENTATION Russian patent published in 2021 - IPC G06T7/50 G06K9/46 

Abstract RU 2745010 C1

FIELD: computing.

SUBSTANCE: invention relates to computing. A method for reconstructing a depth map includes the steps of obtaining an image and a sparse depth map containing depth data; the image feature tensor is calculated by the trained image encoder; calculating the trained depth encoder tensor of depth features; calculating the concatenated feature tensor by the converting module by concatenating the image feature tensor and the depth feature tensor and converting the concatenated features tensor by the transforming module using a predetermined parameter specifying the size of the transformed concatenated feature tensor; predicting a gradient depth map by a trained decoder using the transformed concatenated feature tensor and the tensor; and predicting the dense depth map by the iterative spatial distribution unit using the gradient depth map, the sparse depth map and the tensor obtained in the last upscaling block of the decoder data.

EFFECT: ensuring high quality depth map acquisition on low computing power devices in real time.

21 cl, 10 dwg

Similar patents RU2745010C1

Title Year Author Number
ELIMINATING IMAGE BLUR 2020
  • Anisimovskiy Valery Valerievich
  • Penkin Maksim Alexandrovich
  • Zavalishin Sergey Stanislavovich
  • Gruzdev Aleksei Mikhailovich
  • Dorokhov Evgeny Andreevich
RU2742346C1
METHOD AND APPARATUS FOR JOINT DEBAYERING AND IMAGE NOISE ELIMINATION USING A NEURAL NETWORK 2020
  • Kurmanov Vladimir Gennadievich
  • Fetisov Iurii Gennadievich
  • Petrova Xenya Yurievna
  • Karacharov Ivan Olegovich
  • Lebedev Kirill Victorovich
RU2764395C1
METHOD FOR CONSTRUCTING A SCENE REPRESENTATION WITH DIRECT CORRECTION FOR REAL-TIME IMAGE SYNTHESIS 2022
  • Solovev Pavel Ilyich
  • Korzhenkov Denis Mikhailovich
  • Khakhulin Taras Andreevich
RU2799237C1
IMAGE PROCESSING SYSTEM AND METHOD USING DEEP NEURAL NETWORKS 2018
  • Levinshtein, Alex
  • Chang, Cheng
  • Phung, Edmund
  • Kezele, Irina
  • Guo, Wenzhangzhi
  • Elmoznino, Eric
  • Jiang, Ruowei
  • Aarabi, Parham
RU2743931C1
METHOD FOR PROVIDING COMPUTER VISION 2022
  • Rukhovich Danila Dmitrievich
  • Konushin Anton Sergeevich
  • Konushin Anton Sergeevich
RU2791587C1
METHOD OF BIOMETRIC AUTHENTICATION OF A USER AND A COMPUTING DEVICE IMPLEMENTING SAID METHOD 2018
  • Odinokikh Gleb Andreevich
  • Solomatin Ivan Andreevich
  • Fartukov Aleksei Mikhailovich
  • Efimov Iurii Sergeevich
  • Gnatyuk Vitaly Sergeevich
  • Eremeev Vladimir Alekseevich
  • Yoo Juwoan
  • Lee Kwanghyun
  • Lee Heejun
RU2697646C1
METHOD AND COMPUTING DEVICE FOR FORMATION OF A TRUE DISPLAY OF TIME FLOW OF A DIURNAL SCALE 2020
  • Sterkin Gleb Mikhailovich
  • Solovev Pavel Ilich
  • Silvestrov Aleksei Sergeevich
  • Kharlamov Aleksei Vladislavovich
  • Korzhenkov Denis Mikhailovich
  • Anokhin Ivan Aleksandrovich
  • Khakhulin Taras Andreevich
  • Lempitsky Victor Sergeevich
  • Nikolenko Sergey Igorevich
RU2745209C1
METHOD AND DEVICE FOR IMPROVING SPEECH SIGNAL USING FAST FOURIER CONVOLUTION 2022
  • Shchekotov Ivan Sergeevich
  • Andreev Pavel Konstantinovich
  • Alanov Aibek Arstanbekovich
  • Ivanov Oleg Yurievich
  • Vetrov Dmitry Petrovich
RU2795573C1
SEGMENTATION AND PREDICTION OF TIME PATTERNS OF LOW LEVEL TRAILS 2020
  • Uajting, Ozge Ken
  • Ambati, Radzhiv Bkhatt
  • Uzunbas, Mustafa Gekkhan
  • Khoang, Tkhaj
RU2783420C1
IMAGE RECOGNITION SYSTEM: BEORG SMART VISION 2020
  • Zuev Georgij Alekseevich
  • Kolosov Anton Aleksandrovich
RU2777354C2

RU 2 745 010 C1

Authors

Zavalishin Sergey Stanislavovich

Penkin Maksim Alexandrovich

Gruzdev Aleksei Mikhailovich

Dorokhov Evgeny Andreevich

Begaev Artur Andreevich

Dates

2021-03-18Published

2020-08-25Filed