4 papers · 1 filter
Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding
Sombit Dey, Ozan Unal, Christos Sakaridis +1
3D visual grounding consists of identifying the instance in a 3D scene which is referred by an accompanying language description. While several architectures have been proposed wit…
Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
Wolfgang Boettcher, Lukas Hoyer, Ozan Unal +2
In this work, we introduce Scribbles for All, a label and training data generation algorithm for semantic segmentation trained on scribble labels. Training or fine-tuning semantic…
Discwise Active Learning for LiDAR Semantic Segmentation
Ozan Unal, Dengxin Dai, Ali Tamer Unal +1
While LiDAR data acquisition is easy, labeling for semantic segmentation remains highly time consuming and must therefore be done selectively. Active learning (AL) provides a solut…
LiDAR Meta Depth Completion
Wolfgang Boettcher, Lukas Hoyer, Ozan Unal +2
Depth estimation is one of the essential tasks to be addressed when creating mobile autonomous systems. While monocular depth estimation methods have improved in recent times, dept…