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/GeoNet

GeoNet

Reported on 6 benchmarks across 4 tasks · 1 paper · 5 SOTA

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

Computer Vision4 results

Pose EstimationonKITTI 2015
Average End-Point Error· 2018-03-06
10.81
SOTA
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose arXiv:1803.02276
Camera Pose EstimationonKITTI Odometry Benchmark
Average Rotational Error er[%]· 2018-03-06
9.4
best: 2.205 (Manydepth2)
SOTA
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose arXiv:1803.02276
Camera Pose EstimationonKITTI Odometry Benchmark
Average Translational Error et[%]· 2018-03-06
26.31
best: 7.15 (Manydepth2)
SOTA
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose arXiv:1803.02276
Camera Pose EstimationonKITTI Odometry Benchmark
Absolute Trajectory Error [m]· 2018-03-06
100.75
best: 20.83 (SCIPaD)
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose arXiv:1803.02276

Methodology1 result

3DonKITTI 2015
Average End-Point Error· 2018-03-06
10.81
SOTA
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose arXiv:1803.02276

Audio1 result

1 Image, 2*2 StitchionKITTI 2015
Average End-Point Error· 2018-03-06
10.81
SOTA
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose arXiv:1803.02276