The dimensions of cost volumes and corresponding aggregation networks play a critical role in balancing the speed and accuracy for stereo matching. Current most 2D stereo networks based on 3D cost volumes are speedy but poor in precision, while 3D stereo networks with 4D volumes are slow but precise. To tackle this problem, we propose a novel stereo framework for combining 2D and 3D networks. The disparity range generated by the 2D network is used to guide the 3D network and reduce the computational complexity. Meanwhile, the 3D network can refine the rough disparity from coarse to fine. Through the cooperation of 2D and 3D networks, our method can achieve accurate stereo results at a fast speed. We evaluate our method on three popular public benchmark datasets. Experimental results from the KITTI official website show that, our method can achieve similar accuracy with other 3D stereo networks (PSMNet, GCNet, GwcNet, etc.) at a significantly faster speed. The ablation studies further demonstrate the facticity and reasonability of our propose method.

Stereo matching is an important research field of computer vision. Due to the dimension of cost aggregation, current neural network-based stereo methods are difficult to trade-off speed and accuracy. To this end, we integrate fast 2D stereo methods with accurate 3D networks to improve performance and reduce running time. We leverage a 2D encoder-decoder network to generate a rough disparity map and construct a disparity range to guide the 3D aggregation network, which can significantly improve the accuracy and reduce the computational cost. We use a stacked hourglass structure to refine the disparity from coarse to fine. We evaluated our method on three public datasets. According to the KITTI official website results, Our network can generate an accurate result in 80 ms on a modern GPU. Compared to other 2D stereo networks (AANet, DeepPruner, FADNet, etc.), our network has a big improvement in accuracy. Meanwhile, it is significantly faster than other 3D stereo networks (5× than PSMNet, 7.5× than CSN and 22.5× than GANet, etc.), demonstrating the effectiveness of our method.

In stereo matching, the high-quality cost volume is the key to improve the matching accuracy. Current stereo matching networks only use traditional methods or neural networks to generate one or more cost volumes. They do not consider combining different matching cost computation methods to improve the quality of cost volume. Therefore, we propose BSDCNet, a real-time stereo matching network consisting of two main modules: Double Matching Cost Computation and Bidirectional Cost Aggregation Network. The Double Matching Cost Computation module generates two different cost volumes through traditional methods and neural networks. The Bidirectional Cost Aggregation Network is a two-branch structure, which can aggregate the above two cost volumes with different network depths. Finally, we also design a feature fusion module (FFM) to fuse the two-branch features and use the result for disparity estimation. Our network only uses 3D cost volumes and two-dimensional convolutions. Thus it is much faster than state-of-the-art stereo networks (e.g., 36× than GC-Net, 16× than PSMNet, and 72× than GA-Net). Meanwhile, according to the KITTI official website, our network is more accurate than other fast stereo networks (e.g., Fast DS-CS, RTSNet, and DispNetC), demonstrating that our network can generate a real-time and accurate stereo matching result.

Depth information has long been an important issue in computer vision. The methods for this can be categorized into (1) depth prediction from a single image and (2) binocular stereo matching. However, these two methods are generally regarded as separate tasks, which are accomplished in different network architectures when using deep learning-based methods. This study argues that these two tasks can be achieved using only one network with the same weights. We modify existing networks for stereo matching to perform the two tasks. We first enable the network capable of accepting both a single image and an image pair by duplicating the left image when the right image is absent. Then, we introduce a training procedure that alternatively selects training samples of depth prediction from a single image and binocular stereo matching. In this manner, the trained network can perform both tasks and single-image depth prediction even benefits from stereo matching to achieve better performance. Experimental results on KITTI raw dataset show that our model achieves state-of-the-art performances for accomplishing depth prediction from a single image and binocular stereo matching in the same architecture.

Depth completion is a popular research direction in the field of depth estimation. The fusion of color and depth features is the current critical challenge in this task, mainly due to the asymmetry between the rich scene details in color images and the sparse pixels in depth maps. To tackle this issue, we design an efficient Gated Cross-Attention Network that propagates confidence via a gating mechanism, simultaneously extracting and refining key information in both color and depth branches to achieve local spatial feature fusion. Additionally, we employ an attention network based on the Transformer in low-dimensional space to effectively fuse global features and increase the network's receptive field. With a simple yet efficient gating mechanism, our proposed method achieves fast and accurate depth completion without the need for additional branches or post-processing steps. At the same time, we use the Ray Tune mechanism with the AsyncHyperBandScheduler scheduler and the HyperOptSearch algorithm to automatically search for the optimal number of module iterations, which also allows us to achieve performance comparable to state-of-the-art methods. We conduct experiments on both indoor and outdoor scene datasets. Our fast network achieves Pareto-optimal solutions in terms of time and accuracy, and at the time of submission, our accurate network ranks first among all published papers on the KITTI official website in terms of accuracy.