LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles
Video depth estimation infers the dense scene depth from immediate neighboring video frames. While recent works consider it a simplified structure-from-motion (SfM) problem, it still differs from the SfM in that significantly fewer view angels are available in inference. This setting, however, suits the mono-depth and optical flow estimation. This observation motivates us to decouple the video depth estimation into two components, a normalized pose estimation over a flowmap and a logged residual depth estimation over a mono-depth map. The two parts are unified with an efficient off-the-shelf scale alignment algorithm. Additionally, we stabilize the indoor two-view pose estimation by including additional projection constraints and ensuring sufficient camera translation. Though a two-view algorithm, we validate the benefit of the decoupling with the substantial performance improvement over multi-view iterative prior works on indoor and outdoor datasets. Codes and models are available at https://github.com/ShngJZ/LightedDepth.
PDF AbstractCode
Results from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Monocular Depth Estimation | KITTI Eigen split | LightedDepth (Video Method) | absolute relative error | 0.041 | # 2 | |
RMSE | 1.748 | # 3 | ||||
Sq Rel | 0.107 | # 25 | ||||
RMSE log | 0.059 | # 1 | ||||
Delta < 1.25 | 0.989 | # 1 | ||||
Delta < 1.25^2 | 0.998 | # 1 | ||||
Delta < 1.25^3 | 0.999 | # 11 |