Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SCIPaD

SCIPaD

Reported on 17 benchmarks across 3 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision10 results

Camera Pose EstimationonKITTI Odometry Benchmark
Absolute Trajectory Error [m]· 2024-07-07
20.83
SOTA
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Depth EstimationonKITTI Eigen split unsupervised
Delta < 1.25· 2024-07-07
0.918
best: 0.94 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Depth EstimationonKITTI Eigen split unsupervised
Delta < 1.25^2· 2024-07-07
0.97
best: 0.973 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Depth EstimationonKITTI Eigen split unsupervised
Delta < 1.25^3· 2024-07-07
0.985
best: 0.986 (Jasmine)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Depth EstimationonKITTI Eigen split unsupervised
RMSE· 2024-07-07
4.056
best: 3.662 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Depth EstimationonKITTI Eigen split unsupervised
RMSE log· 2024-07-07
0.166
best: 0.153 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Depth EstimationonKITTI Eigen split unsupervised
Sq Rel· 2024-07-07
0.65
best: 0.785 (Dyna-DM)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Depth EstimationonKITTI Eigen split unsupervised
absolute relative error· 2024-07-07
0.09
best: 0.071 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Camera Pose EstimationonKITTI Odometry Benchmark
Average Rotational Error er[%]· 2024-07-07
3.17
best: 2.205 (Manydepth2)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
Camera Pose EstimationonKITTI Odometry Benchmark
Average Translational Error et[%]· 2024-07-07
8.63
best: 7.15 (Manydepth2)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283

Methodology7 results

3DonKITTI Eigen split unsupervised
Delta < 1.25· 2024-07-07
0.918
best: 0.94 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
3DonKITTI Eigen split unsupervised
Delta < 1.25^2· 2024-07-07
0.97
best: 0.973 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
3DonKITTI Eigen split unsupervised
Delta < 1.25^3· 2024-07-07
0.985
best: 0.986 (Jasmine)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
3DonKITTI Eigen split unsupervised
RMSE· 2024-07-07
4.056
best: 3.662 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
3DonKITTI Eigen split unsupervised
RMSE log· 2024-07-07
0.166
best: 0.153 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
3DonKITTI Eigen split unsupervised
Sq Rel· 2024-07-07
0.65
best: 0.785 (Dyna-DM)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283
3DonKITTI Eigen split unsupervised
absolute relative error· 2024-07-07
0.09
best: 0.071 (SPIdepth)
SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning arXiv:2407.05283