CodeSLAM

We present a new compact but dense representation of scene geometry which is conditioned on the intensity data from a single image and generated from a code consisting of a small number of parameters. We are inspired by work both on learned depth from images, and auto-encoders. Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency. Con- ditioning the depth map on the image means that the code only needs to represent aspects of the local geometry which cannot directly be predicted from the image. We explain how to learn our code representation, and demonstrate its advantageous properties in monocular SLAM.