… Taken the above together, we propose an occlusion aware stereo matching network (OASM-Net).
The network comprises a prior module to reason occlusion and a succeeding module …

… This paper addresses this problem by performing stereo matching on foreground and
background layer separately. Let \(F^f\) denote foreground layer of image F and \(F^b\) denote …

… Taking the above together, we propose an occlusion-aware stereo matching network with
directed disparity smoothness (OASM-DDS). The network, as shown in Fig. 2(a), comprises an …

… facilitated by learningbased stereo-matching algorithms, the … stereo-matching network
called Global Occlusion-Aware … regions, an occlusionaware global aggregation module (OGA…

… Abstract—Stereo … the Occlusion-aware Recurrent binocular Stereo matching (ORStereo),
which deals with these issues by only training on available low disparity range stereo images. …

… dense disparity maps directly from stereo image pairs. However, … stereo matching approach
with a novel occlusion-aware … datasets (Kitti Stereo 2012, Kitti Stereo 2015, Cityscape) and …

… other unsupervised methods for stereo matching. Moreover, our occlusion-aware strategies
can be extended to the other stereo methods conveniently and improve their performances. …

… low-level stereo matching task. In this subsection, we propose an effective auxiliary task for
stereo domain adaptation: self-supervised occlusion-aware … Through occlusionaware stereo …

… warping is the bottleneck of performance improvement for many stereo matching networks.
In this paper, we propose an Occlusion-Aware Refinement Module (OARM), which can learn …

… However, stereo matching networks require a stereo image … to self-supervised stereo
matching methods. This observation … Yuan, “Occlusion aware stereo matching via cooperative un…