collaborators

6 papers

cs.CV2026

Robust Promptable Video Object Segmentation

Sohyun Lee, Yeho Gwon, Lukas Hoyer +3

The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in safety-critical domains. Thi…

cs.CV2026

Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation

Jonas Ernst, Wolfgang Boettcher, Lukas Hoyer +2

We present Rewis3d, a framework that leverages recent advances in feed-forward 3D reconstruction to significantly improve weakly supervised semantic segmentation on 2D images. Obta…

cs.CV2025

S2D: Sparse-To-Dense Keymask Distillation for Unsupervised Video Instance Segmentation

Leon Sick, Lukas Hoyer, Dominik Engel +2

In recent years, the state-of-the-art in unsupervised video instance segmentation has heavily relied on synthetic video data, generated from object-centric image datasets such as I…

cs.CV2025

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.…

cs.CV2025

GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation

Sohyun Lee, Yeho Gwon, Lukas Hoyer +1

Improving robustness of the Segment Anything Model (SAM) to input degradations is critical for its deployment in high-stakes applications such as autonomous driving and robotics. O…

cs.CV2025

From Open-Vocabulary to Vocabulary-Free Semantic Segmentation

Klara Reichard, Giulia Rizzoli, Stefano Gasperini +4

Open-vocabulary semantic segmentation enables models to identify novel object categories beyond their training data. While this flexibility represents a significant advancement, cu…