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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 162 papers

TitleStatusHype
DEFOM-Stereo: Depth Foundation Model Based Stereo MatchingCode3
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo MatchingCode2
X-maps: Direct Depth Lookup for Event-based Structured Light SystemsCode2
MoCha-Stereo: Motif Channel Attention Network for Stereo MatchingCode2
CFNet: Cascade and Fused Cost Volume for Robust Stereo MatchingCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel SupervisionsCode1
3D-LMVIC: Learning-based Multi-View Image Coding with 3D Gaussian Geometric PriorsCode1
Attention-based View Selection Networks for Light-field Disparity EstimationCode1
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow EstimationCode1
Show:102550
← PrevPage 1 of 17Next →
All datasetsSintel 4D LFV - ambushfight5Sintel 4D LFV - bamboo3Sintel 4D LFV - shaman2Sintel 4D LFV - thebigfight2

Benchmark Results

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