AIConfPaper
← Search

Matthias Müller

18 accepted papers

2025

Boxi: Design Decisions in the Context of Algorithmic Performance for Robotics

Jonas Frey, Turcan Tuna, Lanke Frank Tarimo Fu, Cedric Weibel, Katharine Patterson, Benjamin Krummenacher +5
RSS 2025poster

Achieving robust autonomy in mobile robots operating in complex, unstructured environments requires a multimodal sensor suite capable of capturing diverse and complementary information. However, designing such a sensor suite involves multiple critical design decisions, such as sensor selection, comp…

Cited by 1PDF ↗Scholar ↗
2024

Evaluation of Test-Time Adaptation Under Computational Time Constraints

Motasem Alfarra, Hani Itani, Alejandro Pardo, shyma yaser alhuwaider, Merey Ramazanova, Juan Camilo Perez +3
ICML 2024poster

This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to distribution shifts. Though many effective methods have been…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

GIM: Learning Generalizable Image Matcher From Internet Videos

Xuelun Shen, zhipeng cai, Wei Yin, Matthias Müller, Zijun Li, Kaixuan Wang +2
ICLR 2024spotlight

Image matching is a fundamental computer vision problem. While learning-based methods achieve state-of-the-art performance on existing benchmarks, they generalize poorly to in-the-wild images. Such methods typically need to train separate models for different scene types (e.g., indoor vs. outdoor) a…

Cited by 25Source ↗PDF ↗code ↗Scholar ↗
2024

Label Delay in Online Continual Learning

Botos Csaba, Wenxuan Zhang, Matthias Müller, Ser-Nam Lim, Philip Torr, Adel Bibi
NeurIPS 2024poster

Online continual learning, the process of training models on streaming data, has gained increasing attention in recent years. However, a critical aspect often overlooked is the label delay, where new data may not be labeled due to slow and costly annotation processes. We introduce a new continual le…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation

Yujin Chen*, Yinyu Nie, Benjamin Ummenhofer, Reiner Birkl, Michael Paulitsch, Matthias Müller +1
ECCV 2024poster

"We present , an approach to derive ground-truth radiance fields from textured meshes for 3D generation tasks. Many 3D generative approaches represent 3D scenes as radiance fields for training. Their ground-truth radiance fields are usually fitted from multi-view renderings from a large-scale synthe…

Cited by 4Source ↗PDF ↗Scholar ↗
2024

OpenBot-Fleet: A System for Collective Learning with Real Robots

Matthias Müller, Samarth Brahmbhatt, Ankur Deka, Quentin Leboutet, David Hafner, Vladlen Koltun
ICRA 2024poster

We introduce OpenBot-Fleet, a comprehensive open-source cloud robotics system for navigation. OpenBot-Fleet uses smartphones for sensing, local compute and communication, Google Firebase for secure cloud storage and off-board compute, and a robust yet low-cost wheeled robot to act in real-world envi…

Cited by 0Source ↗Scholar ↗
2024

SimCS: Simulation for Domain Incremental Online Continual Segmentation

Motasem Alfarra, Zhipeng Cai, Adel Bibi, Bernard Ghanem, Matthias Müller
AAAI 2024technical

Continual Learning is a step towards lifelong intelligence where models continuously learn from recently collected data without forgetting previous knowledge. Existing continual learning approaches mostly focus on image classification in the class-incremental setup with clear task boundaries and unl…

Cited by 7Source ↗PDF ↗Scholar ↗
2023

E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning

Xiuhong Lin, Changjie Qiu, zhipeng cai, Siqi Shen, Yu Zang, Weiquan Liu +3
NeurIPS 2023poster

Event cameras have emerged as a promising vision sensor in recent years due to their unparalleled temporal resolution and dynamic range. While registration of 2D RGB images to 3D point clouds is a long-standing problem in computer vision, no prior work studies 2D-3D registration for event cameras. T…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2023

Training Efficient Controllers via Analytic Policy Gradient

Nina Wiedemann, Valentin Wüest, Antonio Loquercio, Matthias Müller, Dario Floreano, Davide Scaramuzza
ICRA 2023poster

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but require high computing power. Conversely, learning…

Cited by 23Source ↗code ↗Scholar ↗
2023

Zero-Shot Transfer of Haptics-Based Object Insertion Policies

Samarth Brahmbhatt, Ankur Deka, Andrew Spielberg, Matthias Müller
ICRA 2023poster

Humans naturally exploit haptic feedback during contact-rich tasks like loading a dishwasher or stocking a bookshelf. Current robotic systems focus on avoiding unexpected contact, often relying on strategically placed environment sensors. Recently, contact-exploiting manipulation policies have been…

Cited by 5Source ↗code ↗Scholar ↗
2021

Deep Drone Acrobatics (Extended Abstract)

Elia Kaufmann, Antonio Loquercio, Rene Ranftl, Matthias Müller, Vladlen Koltun, Davide Scaramuzza
IJCAI 2021poster

Acrobatic flight with quadrotors is extremely challenging. Maneuvers such as the loop, matty flip, or barrel roll require high thrust and extreme angular accelerations that push the platform to its limits. Human drone pilots require years of practice to safely master such maneuvers. Yet, a tiny mis…

Cited by 0Source ↗PDF ↗Scholar ↗
2021

Training Graph Neural Networks with 1000 Layers

Guohao Li, Matthias Müller, Bernard Ghanem, Vladlen Koltun
ICML 2021spotlight

Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges. However, memory complexity has become a major obstacle when training deep GNNs for practical applications due to the immense number of nodes, edge…

Cited by 308Source ↗PDF ↗code ↗Scholar ↗
2020

Deep Drone Acrobatics

Elia Kaufmann, Antonio Loquercio, Rene Ranftl, Matthias Müller, Vladlen Koltun, Davide Scaramuzza
RSS 2020poster

Performing acrobatic maneuvers with quadrotors is extremely challenging. Acrobatic flight requires high thrust and extreme angular accelerations that push the platform to its physical limits. Professional drone pilots often measure their level of mastery by flying such maneuvers in competitions. In…

Cited by 201Source ↗PDF ↗code ↗Scholar ↗
2018

End-to-End Driving Via Conditional Imitation Learning

Felipe Codevilla, Matthias Müller, Antonio López, Vladlen Koltun, Alexey Dosovitskiy
ICRA 2018poster

Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upco…

Cited by 1419Source ↗code ↗Scholar ↗