Neural Disparity Refinement for Arbitrary Resolution Stereo
We introduce a novel architecture for neural disparity refinement aimed at facilitating deployment of 3D computer vision on cheap and widespread consumer devices, such as mobile phones. Our approach relies on a continuous formulation that enables to estimate a refined disparity map at any arbitrary output resolution. Thereby, it can handle effectively the unbalanced camera setup typical of nowadays mobile phones, which feature both high and low resolution RGB sensors within the same device. Moreover, our neural network can process seamlessly the output of a variety of stereo methods and, by refining the disparity maps computed by a traditional matching algorithm like SGM, it can achieve unpaired zero-shot generalization performance compared to state-of-the-art end-to-end stereo models.
Code (1)
Tasks
Zero-shot GeneralizationSimilar Papers 제목 키워드 기반
ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images
Stereo reconstruction models trained on small images do not generalize well to high-resolution data. Training a model on high-resolution image size faces difficulties of data availability and is often infeasible due to l…
4kGPUStereo MatchingA Decomposition Model for Stereo Matching
In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases. In order to reduce the huge cost of s…
Disparity EstimationmodelStereo MatchingSMD-Nets: Stereo Mixture Density Networks
Despite stereo matching accuracy has greatly improved by deep learning in the last few years, recovering sharp boundaries and high-resolution outputs efficiently remains challenging. In this paper, we propose Stereo Mixt…
Disparity EstimationStereo MatchingURS-Stereo: Uncertainty-Guided Residual Search for Real-Time Stereo Matching
Real-time stereo matching is crucial for robotics, autonomous systems, and embedded vision applications, where both computational efficiency and disparity accuracy are required. Recent coarse-to-fine stereo matching meth…
Computational EfficiencyDisparity EstimationStereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo matching that runs at 60 fps on an NVidia Titan X, producing high-quality, edge-preserved, quantization-free disparity maps. A ke…
Depth EstimationDepth PredictionQuantizationStereo Depth Estimation+2