Uncertainty guided adaptive warping for robust and efficient stereo matching
Correlation based stereo matching has achieved outstanding performance, which pursues
cost volume between two feature maps. Unfortunately, current methods with a fixed trained …
cost volume between two feature maps. Unfortunately, current methods with a fixed trained …
DualRefine: Self-supervised depth and pose estimation through iterative epipolar sampling and refinement toward equilibrium
A Bangunharcana, A Magd… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Self-supervised multi-frame depth estimation achieves high accuracy by computing
matching costs of pixel correspondences between adjacent frames, injecting geometric …
matching costs of pixel correspondences between adjacent frames, injecting geometric …
Mc-stereo: Multi-peak lookup and cascade search range for stereo matching
Stereo matching is a fundamental task in scene comprehension. In recent years, the method
based on iterative optimization has shown promise in stereo matching. However, the current …
based on iterative optimization has shown promise in stereo matching. However, the current …
Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality
Abstract Real-time Stereo Matching is a cornerstone task for Extended Reality (XR)
applications, such as 3D scene understanding, video pass-through, and mixed-reality …
applications, such as 3D scene understanding, video pass-through, and mixed-reality …
VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors
We present a stereo-matching method for depth estimation from high-resolution images
using visual hulls as priors, and a memory-efficient technique for the correlation …
using visual hulls as priors, and a memory-efficient technique for the correlation …
DCVSMNet: Double Cost Volume Stereo Matching Network
We introduce Double Cost Volume Stereo Matching Network (DCVSMNet) which is a novel
architecture characterised by by two small upper (group-wise) and lower (norm correlation) …
architecture characterised by by two small upper (group-wise) and lower (norm correlation) …
[PDF][PDF] Deep Equilibrium Model for Memory Efficient Stereo Matching on the High Resolution Argoverse Dataset
The estimation of depth from stereo image pairs is a longstanding computer vision task with
applications in robotics [12, 13]. In this report, we are interested in building a stereo …
applications in robotics [12, 13]. In this report, we are interested in building a stereo …