… belief propagation algorithm on edge regions. To deal with the time consumption issue of the
standard belief propagation … This constraint does not degrade the matching results and can …

In this work, we propose BP-MVSNet, a convolutional neural network (CNN)-based Multi-View-Stereo
(MVS) method that uses a differentiable Conditional Random Field (CRF) layer for …

… sparse cues (left) with the guidance of RGB images (middle). The expanded disparity maps
help improve stereo matching … sparse LiDAR data as guidance for existing stereo matching …

… Abstract: Stereo matching between two images is done by computing disparity of all points
… The accuracy of the object while selecting feature is missing which yields to sparse disparity …

… selection problem and proposed a method called local sparse matching (LSM). By imposing
… belief propagation, but our method directly used belief propagation to compute the matching …

… Most stereo matching models, such as PSM-Net, GA-Net, and AA-Net, can be easily …
Experiments on multiple benchmark datasets show that our method improves stereo matching …

… of the sparse matching results. Benefiting from the epipolar rectification characteristics of
stereo … Men, “Double propagation stereo matching for urban 3-D reconstruction from satellite …

… fusion, the authors of [29] present the fusion problem as a Belief Propagation (BP) by using
Markov Random Filed (MRF), where the weights correspond to confidence in each sensor’s …

… dictionary learning (PDL) and sparse signal recovery (SSR) problem … ) sparse Bayesian
learning framework. 3) We provide a fast iterative update for the hyperparameters of the sparse …

… This paper proposed SCV-Stereo, a novel stereo matching network that adopts a sparse
cost volume representation learning scheme and an iterative disparity update scheme. Our ap…