DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mapping A method for large-scale 3D scene reconstruction from sparse 3D LiDAR scans. Project: https://t.co/Mh1zj0P9KF Vid: https://t.co/OGITkxikxi Text: https://t.co/N6EzCrBvFA

We leverage multi-modal self-supervised features and perform graph-cuts to generate instance proposals. These initial proposals are further refined with a self-training algorithm. Joint w/ @CedricPerauer, Laurenz Heidrich, Haifan Zhang, @MattNiessner , and Anastasiia Kornilova

AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans A method for unsupervised instance segmentation of 3D outdoor LiDAR scenes. Project: https://t.co/m8DJanWH2T Vid: https://t.co/Z9OyZbskdJ Paper : https://t.co/rrmvQdjmWV