37 papers with code • 4 benchmarks • 3 datasets
The Disparity Estimation is the task of finding the pixels in the multiscopic views that correspond to the same 3D point in the scene.
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively.
The second part performs matching cost calculation, matching cost aggregation and disparity calculation to estimate the initial disparity using shared features.
However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained.
In computer vision, superpixels have been widely used as an effective way to reduce the number of image primitives for subsequent processing.
In this paper, we propose CFNet, a Cascade and Fused cost volume based network to improve the robustness of the stereo matching network.
Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles.
Instead, we propose a generic architecture that decomposes the label improvement task to three steps: 1) detecting the initial label estimates that are incorrect, 2) replacing the incorrect labels with new ones, and finally 3) refining the renewed labels by predicting residual corrections w. r. t.
The success of these methods is due to the availability of training data with ground truth; training learning-based systems on these datasets has allowed them to surpass the accuracy of conventional approaches based on heuristics and assumptions.