Depth- and Semantics-aware Multi-modal Domain Translation: Generating 3D Panoramic Color Images from LiDAR Point Clouds

arXiv:2302.07661v4 Announce Type: replace
Abstract: This work presents a new depth- and semantics-aware conditional generative model, named TITAN-Next, for cross-domain image-to-image translation in a multi-modal setup between LiDAR and camera sensors. The proposed model leverages scene semantics as a mid-level representation and is able to translate raw LiDAR point clouds to RGB-D camera images by solely relying on semantic scene segments. We claim that this is the first framework of its kind and it has practical applications in autonomous vehicles …

abstract arxiv color cs.cv domain generative image images image-to-image image-to-image translation lidar modal multi-modal next representation semantics sensors setup titan translation type work