collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2025

NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction

Thomas Monninger, Zihan Zhang, Steffen Staab +1

Accurate environmental representations are essential for autonomous driving, providing the foundation for safe and efficient navigation. Traditionally, high-definition (HD) maps ar…

cs.CV2025

Uncertainty Matters in Dynamic Gaussian Splatting for Monocular 4D Reconstruction

Fengzhi Guo, Chih-Chuan Hsu, Sihao Ding +1

Reconstructing dynamic 3D scenes from monocular input is fundamentally under-constrained, with ambiguities arising from occlusion and extreme novel views. While dynamic Gaussian Sp…

cs.CV2025

Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations

Sihao Ding, Santosh Vasa, Aditi Ramadwar

Vision-Language Models (VLMs) often produce fluent Natural Language Explanations (NLEs) that sound convincing but may not reflect the causal factors driving predictions. This misma…

cs.CV2025

MapDiffusion: Generative Diffusion for Vectorized Online HD Map Construction and Uncertainty Estimation in Autonomous Driving

Thomas Monninger, Zihan Zhang, Zhipeng Mo +3

Autonomous driving requires an understanding of the static environment from sensor data. Learned Bird's-Eye View (BEV) encoders are commonly used to fuse multiple inputs, and a vec…

cs.CV2025

AutoVDC: Automated Vision Data Cleaning Using Vision-Language Models

Santosh Vasa, Aditi Ramadwar, Jnana Rama Krishna Darabattula +5

Training of autonomous driving systems requires extensive datasets with precise annotations to attain robust performance. Human annotations suffer from imperfections, and multiple…

cs.CV2025

AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Construction

Thomas Monninger, Md Zafar Anwar, Stanislaw Antol +2

Autonomous driving requires understanding infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-tim…