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/LightDepth

LightDepth

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision3 results

Depth EstimationonKITTI Eigen split
Number of parameters (M)· 2022-11-16
42.6
SOTA
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning arXiv:2211.08608
Depth EstimationonKITTI Eigen split
RMSE· 2022-11-16
2.923
best: 1.394 (SPIDepth)
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning arXiv:2211.08608
Depth EstimationonKITTI Eigen split
absolute relative error· 2022-11-16
0.07
best: 0.029 (SPIDepth)
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning arXiv:2211.08608

Methodology3 results

3DonKITTI Eigen split
Number of parameters (M)· 2022-11-16
42.6
SOTA
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning arXiv:2211.08608
3DonKITTI Eigen split
RMSE· 2022-11-16
2.923
best: 1.394 (SPIDepth)
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning arXiv:2211.08608
3DonKITTI Eigen split
absolute relative error· 2022-11-16
0.07
best: 0.029 (SPIDepth)
LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning arXiv:2211.08608