10 papers
Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds
Bin Yang, Mohamed Abdelsamad, Miao Zhang +1
Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize seman…
SparseLaneSTP: Leveraging Spatio-Temporal Priors with Sparse Transformers for 3D Lane Detection
Maximilian Pittner, Joel Janai, Mario Faigle +1
3D lane detection has emerged as a critical challenge in autonomous driving, encompassing identification and localization of lane markings and the 3D road surface. Conventional 3D…
When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks
Steffen Hagedorn, Luka Donkov, Aron Distelzweig +1
Planner evaluation in closed-loop simulation often uses rule-based traffic agents, whose simplistic and passive behavior can hide planner deficiencies and bias rankings. Widely use…
PseudoMapTrainer: Learning Online Mapping without HD Maps
Christian Löwens, Thorben Funke, Jingchao Xie +1
Online mapping models show remarkable results in predicting vectorized maps from multi-view camera images only. However, all existing approaches still rely on ground-truth high-def…
Variance-Based Pruning for Accelerating and Compressing Trained Networks
Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache
Increasingly expensive training of ever larger models such as Vision Transfomers motivate reusing the vast library of already trained state-of-the-art networks. However, their late…
Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks
Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache
Vision Transformers have emerged as the state-of-the-art models in various Computer Vision tasks, but their high computational and resource demands pose significant challenges. Whi…