351 citations · 1.3k across the 22 of their papers we have counts for
27 papers
Monocular Visual-Inertial Depth Estimation
Diana Wofk, René Ranftl, Matthias Müller +1
We present a visual-inertial depth estimation pipeline that integrates monocular depth estimation and visual-inertial odometry to produce dense depth estimates with metric scale. O…
Unsupervised Contrastive Domain Adaptation for Semantic Segmentation
Feihu Zhang, Vladlen Koltun, Philip Torr +2
Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptati…
Language-driven Semantic Segmentation
Boyi Li, Kilian Q. Weinberger, Serge Belongie +2
We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "buildi…
Transferable End-to-end Room Layout Estimation via Implicit Encoding
Hao Zhao, Rene Ranftl, Yurong Chen +1
We study the problem of estimating room layouts from a single panorama image. Most former works have two stages: feature extraction and parametric model fitting. Here we propose an…
Learning High-Speed Flight in the Wild
Antonio Loquercio, Elia Kaufmann, René Ranftl +3
Quadrotors are agile. Unlike most other machines, they can traverse extremely complex environments at high speeds. To date, only expert human pilots have been able to fully exploit…
An Analysis of Super-Net Heuristics in Weight-Sharing NAS
Kaicheng Yu, René Ranftl, Mathieu Salzmann
Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design…
Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search
Kaicheng Yu, Rene Ranftl, Mathieu Salzmann
Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware. However, recent works have empirically s…
Vision Transformers for Dense Prediction
René Ranftl, Alexey Bochkovskiy, Vladlen Koltun
We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble…
Deep Drone Acrobatics
Elia Kaufmann, Antonio Loquercio, René Ranftl +3
Performing acrobatic maneuvers with quadrotors is extremely challenging. Acrobatic flight requires high thrust and extreme angular accelerations that push the platform to its physi…
High-dimensional Convolutional Networks for Geometric Pattern Recognition
Christopher Choy, Junha Lee, Rene Ranftl +2
Many problems in science and engineering can be formulated in terms of geometric patterns in high-dimensional spaces. We present high-dimensional convolutional networks (ConvNets)…
How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS
Kaicheng Yu, Rene Ranftl, Mathieu Salzmann
Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design…
Safe Robot Navigation via Multi-Modal Anomaly Detection
Lorenz Wellhausen, René Ranftl, Marco Hutter
Navigation in natural outdoor environments requires a robust and reliable traversability classification method to handle the plethora of situations a robot can encounter. Binary cl…
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
René Ranftl, Katrin Lasinger, David Hafner +2
The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different envir…
High Speed and High Dynamic Range Video with an Event Camera
Henri Rebecq, René Ranftl, Vladlen Koltun +1
Event cameras are novel sensors that report brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with…
What Do Single-view 3D Reconstruction Networks Learn?
Maxim Tatarchenko, Stephan R. Richter, René Ranftl +3
Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by…
Deep Drone Racing: From Simulation to Reality with Domain Randomization
Antonio Loquercio, Elia Kaufmann, René Ranftl +3
Dynamically changing environments, unreliable state estimation, and operation under severe resource constraints are fundamental challenges that limit the deployment of small autono…
Feedback MPC for Torque-Controlled Legged Robots
Ruben Grandia, Farbod Farshidian, René Ranftl +1
The computational power of mobile robots is currently insufficient to achieve torque level whole-body Model Predictive Control (MPC) at the update rates required for complex dynami…
Events-to-Video: Bringing Modern Computer Vision to Event Cameras
Henri Rebecq, René Ranftl, Vladlen Koltun +1
Event cameras are novel sensors that report brightness changes in the form of asynchronous "events" instead of intensity frames. They have significant advantages over conventional…
Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing
Elia Kaufmann, Mathias Gehrig, Philipp Foehn +4
Autonomous micro aerial vehicles still struggle with fast and agile maneuvers, dynamic environments, imperfect sensing, and state estimation drift. Autonomous drone racing brings t…
Frequency-Aware Model Predictive Control
Ruben Grandia, Farbod Farshidian, Alexey Dosovitskiy +2
Transferring solutions found by trajectory optimization to robotic hardware remains a challenging task. When the optimization fully exploits the provided model to perform dynamic t…
Deep Drone Racing: Learning Agile Flight in Dynamic Environments
Elia Kaufmann, Antonio Loquercio, Rene Ranftl +3
Autonomous agile flight brings up fundamental challenges in robotics, such as coping with unreliable state estimation, reacting optimally to dynamically changing environments, and…
Accurate Optical Flow via Direct Cost Volume Processing
Jia Xu, René Ranftl, Vladlen Koltun
We present an optical flow estimation approach that operates on the full four-dimensional cost volume. This direct approach shares the structural benefits of leading stereo matchin…
Techniques for Gradient Based Bilevel Optimization with Nonsmooth Lower Level Problems
Peter Ochs, René Ranftl, Thomas Brox +1
We propose techniques for approximating bilevel optimization problems with non-smooth lower level problems that can have a non-unique solution. To this end, we substitute the expre…
A higher-order MRF based variational model for multiplicative noise reduction
Yunjin Chen, Wensen Feng, René Ranftl +2
The Fields of Experts (FoE) image prior model, a filter-based higher-order Markov Random Fields (MRF) model, has been shown to be effective for many image restoration problems. Mot…