Author

Hanno Gottschalk

h-index 8 View on Semantic Scholar

We have 3 of 32 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Diffuse2Seg: Diffusion Models Can Segment Anything Without Supervision

Diffuse2Seg is introduced, which repurposes generative diffusion models for automatic mask generation by propagating a grid of point prompts through their self-attention representations in an edge-preserving manner, and shows that a model trained on Diffuse2Seg labels provides a strong initialization for semi-supervise...

Christoph Hümmer, Joachim Sicking, Fabian Hüger et al. · 0 citations

Preprint Aug 2026

RoG-DAgger: Rollout-Guided Post-Training for End-to-End Driving

RoG-DAgger is introduced, a post-training framework that uses short-horizon kinematic rollouts to construct high-quality expert demonstrations in safety-critical states and aligns the expert's field of view with that of the student to provide student-compatible supervision.

Liangyu Zhong, Joachim Sicking, Fabian Hueger et al. · 0 citations

Preprint Aug 2026

Extended Field of View Analysis for VideoGAN-based Trajectory Generation

This paper builds upon previous work on generative adversarial network (GAN)-based semantic bird's-eye-view traffic generation and extends the proposed framework in several key aspects, improving the semantic representation, replacing the trajectory extraction procedure with a graph-based association method, and system...

Annajoyce Mariani, Kira Maag, Hanno Gottschalk · 0 citations