7 papers · 1 filter
RealDriveSim: A Realistic Multi-Modal Multi-Task Synthetic Dataset for Autonomous Driving
Arpit Jadon, Haoran Wang, Phillip Thomas +7
As perception models continue to develop, the need for large-scale datasets increases. However, data annotation remains far too expensive to effectively scale and meet the demand.…
Burst Image Super-Resolution with Mamba
Ozan Unal, Steven Marty, Dengxin Dai
Burst image super-resolution (BISR) aims to enhance the resolution of a keyframe by leveraging information from multiple low-resolution images captured in quick succession. In the…
Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation
Elham Amin Mansour, Ozan Unal, Suman Saha +2
The increasing relevance of panoptic segmentation is tied to the advancements in autonomous driving and AR/VR applications. However, the deployment of such models has been limited…
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…
Bayesian Self-Training for Semi-Supervised 3D Segmentation
Ozan Unal, Christos Sakaridis, Luc Van Gool
3D segmentation is a core problem in computer vision and, similarly to many other dense prediction tasks, it requires large amounts of annotated data for adequate training. However…
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…