key elements
problems
code
The disadvantages of droid slam
- bad performance on KITTI
- extremely graphics card memory consumption/video frames limitation
- Does the runtime is efficient enough?
Why does this happen?
1.1 Generalization performance problem
1.2 feature points near/faraway to baseline, monocular`=stereoHow can we solve it?
Literature review
- RAFT, optical flow
- DeepV2D alternates between updating depth and updating camera poses, instead of bundle adjustment.
- BA-Net has bundle adjustment layer which is not dense.
- Multi-view optimization of local feature geometry: builds a neural network into the SfM pipeline to improve keypoint localization accuracy.
- gradslam: dense slam meets automatic differentiation, differentiable computation graphs, error backpropagated to sensor. Differentiale, no trainable parameters.
- DeepFactors, most complete deep SLAM, performs joint optimization of pose and depth, capable of loop closure.
- CodeSLAMa