Depth Completion
The Depth Completion task is a sub-problem of depth estimation. In the sparse-to-dense depth completion problem, one wants to infer the dense depth map of a 3-D scene given an RGB image and its corresponding sparse reconstruction in the form of a sparse depth map obtained either from computational methods such as SfM (Strcuture-from-Motion) or active sensors such as lidar or structured light sensors.
Source: LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery , Unsupervised Depth Completion from Visual Inertial Odometry
Papers
Showing 1–10 of 242 papers
All datasetsKITTI Depth CompletionVOIDNYU-Depth V2Matterport3DKITTIKITTI Depth Completion 500 pointsKITTI Depth Completion Eigen SplitPLADVOID-150
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SparseConvs | RMSE | 1,601 | — | Unverified |
| 2 | NConv-CNN | RMSE | 1,268 | — | Unverified |
| 3 | VOICED | RMSE | 1,169.97 | — | Unverified |
| 4 | ScaffNet-FusionNet | RMSE | 1,121.93 | — | Unverified |
| 5 | KBNet | RMSE | 1,069.47 | — | Unverified |
| 6 | Spade-sD | RMSE | 1,035 | — | Unverified |
| 7 | HMS-Net | RMSE | 937 | — | Unverified |
| 8 | Spade-RGBsD | RMSE | 918 | — | Unverified |
| 9 | NConv-CNN-L1 | RMSE | 859 | — | Unverified |
| 10 | NConv-CNN-L2 | RMSE | 830 | — | Unverified |