HCVNet: Binocular Stereo Matching via Hybrid Cost Volume Computation Module With Attention

Binocular stereo matching, a computer vision task typically using cost volume constructed from the left and right feature maps to estimate disparity and depth, is widely applied in 3D reconstruction, autonomous driving and robotics navigation. Though recent study brings an awareness of the convoluti...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Chenglin Dai, Qingling Chang, Tian Qiu, Xinglin Liu, Yan Cui
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2022-01-01
Colecção:	IEEE Access
Assuntos:	Binocular stereo matching feature map channel-wise independencies channel attention cost volume
Acesso em linha:	https://ieeexplore.ieee.org/document/9870784/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!