9 papers
LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection
Johannes Meier, Jonathan Michel, Oussema Dhaouadi +7
Real-time monocular 3D object detection remains challenging due to severe depth ambiguity, viewpoint shifts, and the high computational cost of 3D reasoning. Existing approaches ei…
Scene-Centric Unsupervised Video Panoptic Segmentation
Christoph Reich, Oliver Hahn, Nikita Araslanov +4
Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task se…
MARCO: Navigating the Unseen Space of Semantic Correspondence
Claudia Cuttano, Gabriele Trivigno, Carlo Masone +1
Recent advances in semantic correspondence rely on dual-encoder architectures, combining DINOv2 with diffusion backbones. While accurate, these billion-parameter models generalize…
INSID3: Training-Free In-Context Segmentation with DINOv3
Claudia Cuttano, Gabriele Trivigno, Christoph Reich +3
In-context segmentation (ICS) aims to segment arbitrary concepts, e.g., objects, parts, or personalized instances, given one annotated visual examples. Existing work relies on (i)…
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model
Jannik Endres, Oliver Hahn, Charles Corbière +3
Omnidirectional depth perception is essential for mobile robotics applications that require scene understanding across a full 360° field of view. Camera-based setups offer a cost-…
A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation
Denis Zavadski, Damjan Kalšan, Tim Küchler +3
Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly…