SOTAVerified

Disparity Estimation

The Disparity Estimation is the task of finding the pixels in the multiscopic views that correspond to the same 3D point in the scene.

Papers

Showing 5175 of 162 papers

TitleStatusHype
EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection0
EDNet: Efficient Disparity Estimation with Cost Volume Combination and Attention-based Spatial Residual0
Analytic Signal Phase in N-D by Linear Symmetry Tensor--fingerprint modeling0
End-to-End Learning of Multi-scale Convolutional Neural Network for Stereo Matching0
Light Field Super-Resolution Via Graph-Based Regularization0
Low Compute and Fully Parallel Computer Vision With HashMatch0
AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks0
Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis0
Disparity estimation for fisheye images with an application to intermediate view synthesis0
FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks0
Fast Disparity Estimation from a Single Compressed Light Field Measurement0
Deep 3D-Zoom Net: Unsupervised Learning of Photo-Realistic 3D-Zoom0
Blur-Aware Disparity Estimation From Defocus Stereo Images0
Learning Light Field Reconstruction from a Single Coded Image0
Disparity-Aware Domain Adaptation in Stereo Image Restoration0
Disentangling Light Fields for Super-Resolution and Disparity Estimation0
All-directional Disparity Estimation for Real-world QPD Images0
DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning0
ADCPNet: Adaptive Disparity Candidates Prediction Network for Efficient Real-Time Stereo Matching0
Learning based Deep Disentangling Light Field Reconstruction and Disparity Estimation Application0
Left-Right Comparative Recurrent Model for Stereo Matching0
Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision0
Investigating Spherical Epipolar Rectification for Multi-View Stereo 3D Reconstruction0
IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images0
Hyperspectral Light Field Stereo Matching0
Show:102550
← PrevPage 3 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Two-stream CNN+CLSTMBadPix(0.01)62.05Unverified
#ModelMetricClaimedVerifiedStatus
1Two-stream CNN+CLSTMBadPix(0.01)53.3Unverified
#ModelMetricClaimedVerifiedStatus
1Two-stream CNN+CLSTMBadPix(0.01)74.77Unverified
#ModelMetricClaimedVerifiedStatus
1Two-stream CNN+CLSTMBadPix(0.01)17.75Unverified