Related papers: Displacement-Invariant Cost Computation for Effici…
Depth estimation is a cornerstone of a vast number of applications requiring 3D assessment of the environment, such as robotics, augmented reality, and autonomous driving to name a few. One prominent technique for depth estimation is stereo…
Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost…
The integral image, an intermediate image representation, has found extensive use in multi-scale local feature detection algorithms, such as Speeded-Up Robust Features (SURF), allowing fast computation of rectangular features at constant…
Stereo dense image matching can be categorized to low-level feature based matching and deep feature based matching according to their matching cost metrics. Census has been proofed to be one of the most efficient low-level feature based…
Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo matching models that deliver high accuracy while operating in real-time continues to be a major challenge in…
Deep neural networks have shown excellent performance in stereo matching task. Recently CNN-based methods have shown that stereo matching can be formulated as a supervised learning task. However, less attention is paid on the fusion of…
Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address…
Stereo matching has emerged as a cost-effective solution for road surface 3D reconstruction, garnering significant attention towards improving both computational efficiency and accuracy. This article introduces decisive disparity diffusion…
Efficient real-time disparity estimation is critical for the application of stereo vision systems in various areas. Recently, stereo network based on coarse-to-fine method has largely relieved the memory constraints and speed limitations of…
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception. Instead of directly fusing estimated depths across LiDAR and stereo…
Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset…
We present an iterative inverse reinforcement learning algorithm to infer optimal cost functions in continuous spaces. Based on a popular maximum entropy criteria, our approach iteratively finds a weight improvement step and proposes a…
Both uncertainty-assisted and iteration-based methods have achieved great success in stereo matching. However, existing uncertainty estimation methods take a single image and the corresponding disparity as input, which imposes higher…
Convolutional neural networks(CNN) have been shown to perform better than the conventional stereo algorithms for stereo estimation. Numerous efforts focus on the pixel-wise matching cost computation, which is the important building block…
We present a real-time, non-learning depth estimation method that fuses Light Detection and Ranging (LiDAR) data with stereo camera input. Our approach comprises three key techniques: Semi-Global Matching (SGM) stereo with Discrete…
Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utilization of extracted image features and a spatially varying…
The desire for wide-field of view, large fractional bandwidth, high sensitivity, high spectral and temporal resolution has driven radio interferometry to the point of big data revolution where the data is represented in at least three…
Multi-view stereo is an important research task in computer vision while still keeping challenging. In recent years, deep learning-based methods have shown superior performance on this task. Cost volume pyramid network-based methods which…
Estimating correspondences between pairs of non-rigid deformable 3D shapes remains a significant challenge in computer vision and graphics. While deep functional map methods have become the go-to solution for addressing this problem, they…
Recent methods in stereo matching have continuously improved the accuracy using deep models. This gain, however, is attained with a high increase in computation cost, such that the network may not fit even on a moderate GPU. This issue…