Dropping the D: RGB-D SLAM Without the Depth Sensor
This work addresses the need for simpler and more cost-effective SLAM systems by potentially replacing active depth sensors with vision models, though it is incremental as it builds on existing RGB-D SLAM back ends.
The authors tackled the problem of achieving RGB-D-level accuracy in SLAM without depth sensors by developing DropD-SLAM, which uses pretrained vision modules to replace depth input, resulting in 7.4 cm mean ATE on static sequences and 1.8 cm on dynamic sequences while operating at 22 FPS.
We present DropD-SLAM, a real-time monocular SLAM system that achieves RGB-D-level accuracy without relying on depth sensors. The system replaces active depth input with three pretrained vision modules: a monocular metric depth estimator, a learned keypoint detector, and an instance segmentation network. Dynamic objects are suppressed using dilated instance masks, while static keypoints are assigned predicted depth values and backprojected into 3D to form metrically scaled features. These are processed by an unmodified RGB-D SLAM back end for tracking and mapping. On the TUM RGB-D benchmark, DropD-SLAM attains 7.4 cm mean ATE on static sequences and 1.8 cm on dynamic sequences, matching or surpassing state-of-the-art RGB-D methods while operating at 22 FPS on a single GPU. These results suggest that modern pretrained vision models can replace active depth sensors as reliable, real-time sources of metric scale, marking a step toward simpler and more cost-effective SLAM systems.