相关论文: Real-Time Subpixel Fast Bilateral Stereo

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 key insight of this…

In this work, we concentrate on exciting the intrinsic local consistency of stereo matching through the incorporation of superpixel soft constraints, with the objective of mitigating inaccuracies at the boundaries of predicted disparity…

We present a novel stereo vision algorithm that is capable of obstacle detection on a mobile-CPU processor at 120 frames per second. Our system performs a subset of standard block-matching stereo processing, searching only for obstacles at…

Stereo-based depth estimation is a cornerstone of computer vision, with state-of-the-art methods delivering accurate results in real time. For several applications such as autonomous navigation, however, it may be useful to trade accuracy…

Video stereo matching is the task of estimating consistent disparity maps from rectified stereo videos. There is considerable scope for improvement in both datasets and methods within this area. Recent learning-based methods often focus on…

With the popularity of stereo cameras in computer assisted surgery techniques, a second viewpoint would provide additional information in surgery. However, how to effectively access and use stereo information for the super-resolution (SR)…

We present a novel framework to learn to convert the perpixel photometric information at each view into spatially distinctive and view-invariant low-level features, which can be plugged into existing multi-view stereo pipeline for enhanced…

Deep neural networks have shown excellent performance for stereo matching. Many efforts focus on the feature extraction and similarity measurement of the matching cost computation step while less attention is paid on cost aggregation which…

Our goal is to significantly speed up the runtime of current state-of-the-art stereo algorithms to enable real-time inference. Towards this goal, we developed a differentiable PatchMatch module that allows us to discard most disparities…

The segmentation of video sequences into foreground and background regions is a low-level process commonly used in video content analysis and smart surveillance applications. Using a multispectral camera setup can improve this process by…

Performance is a critical challenge in mobile image processing. Given a reference imaging pipeline, or even human-adjusted pairs of images, we seek to reproduce the enhancements and enable real-time evaluation. For this, we introduce a new…

This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition. Given a deep multi-view stereo network, our…

This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not…

In many domains that involve the use of sensors, such as robotics or sensor networks, there are opportunities to use some form of active sensing to disambiguate data from noisy or unreliable sensors. These disambiguating actions typically…

Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching or optical flow. The application of self-supervised…

Deep learning has made significant impacts on multi-view stereo systems. State-of-the-art approaches typically involve building a cost volume, followed by multiple 3D convolution operations to recover the input image's pixel-wise depth.…

The pursuit of a generalizable stereo matching model, capable of performing well across varying resolutions and disparity ranges without dataset-specific fine-tuning, has revealed a fundamental trade-off. Iterative local search methods…

Retrieving the missing dimension information in acoustic images from 2D forward-looking sonar is a well-known problem in the field of underwater robotics. There are works attempting to retrieve 3D information from a single image which…

Although the number of camera-based sensors mounted on vehicles has recently increased dramatically, robust and accurate object velocity detection is difficult. Additionally, it is still common to use radar as a fusion system. We have…

Stereo vision generally involves the computation of pixel correspondences and estimation of disparities between rectified image pairs. In many applications, including simultaneous localization and mapping (SLAM) and 3D object detection, the…