53 citations · 227 across the 37 of their papers we have counts for
14 papers · 1 filter
Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes
Ayça Takmaz, Danda Pani Paudel, Thomas Probst +3
Monocular depth reconstruction of complex and dynamic scenes is a highly challenging problem. While for rigid scenes learning-based methods have been offering promising results eve…
DeepSurfels: Learning Online Appearance Fusion
Marko Mihajlovic, Silvan Weder, Marc Pollefeys +1
We present DeepSurfels, a novel hybrid scene representation for geometry and appearance information. DeepSurfels combines explicit and neural building blocks to jointly encode geom…
FMODetect: Robust Detection of Fast Moving Objects
Denys Rozumnyi, Jiri Matas, Filip Sroubek +2
We propose the first learning-based approach for fast moving objects detection. Such objects are highly blurred and move over large distances within one video frame. Fast moving ob…
Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Image
Zuoyue Li, Zhenqiang Li, Zhaopeng Cui +3
We present a novel method for synthesizing both temporally and geometrically consistent street-view panoramic video from a single satellite image and camera trajectory. Existing cr…
DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari +2
Objects moving at high speed appear significantly blurred when captured with cameras. The blurry appearance is especially ambiguous when the object has complex shape or texture. In…
NeuralFusion: Online Depth Fusion in Latent Space
Silvan Weder, Johannes L. Schönberger, Marc Pollefeys +1
We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation…
Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion
Ivan Tishchenko, Sandro Lombardi, Martin R. Oswald +1
Most of the current scene flow methods choose to model scene flow as a per point translation vector without differentiating between static and dynamic components of 3D motion. In t…
Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors
Cathrin Elich, Martin R. Oswald, Marc Pollefeys +1
Representing scenes at the granularity of objects is a prerequisite for scene understanding and decision making. We propose PriSMONet, a novel approach based on Prior Shape knowled…
KAPLAN: A 3D Point Descriptor for Shape Completion
Audrey Richard, Ian Cherabier, Martin R. Oswald +2
We present a novel 3D shape completion method that operates directly on unstructured point clouds, thus avoiding resource-intensive data structures like voxel grids. To this end, w…
Online Invariance Selection for Local Feature Descriptors
Rémi Pautrat, Viktor Larsson, Martin R. Oswald +1
To be invariant, or not to be invariant: that is the question formulated in this work about local descriptors. A limitation of current feature descriptors is the trade-off between…
AdaLAM: Revisiting Handcrafted Outlier Detection
Luca Cavalli, Viktor Larsson, Martin Ralf Oswald +2
Local feature matching is a critical component of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization. However, due to limit…
Accurate Mapping and Planning for Autonomous Racing
Leiv Andresen, Adrian Brandemuehl, Alex Hönger +11
This paper presents the perception, mapping, and planning pipeline implemented on an autonomous race car. It was developed by the 2019 AMZ driverless team for the Formula Student G…
Learned Multi-View Texture Super-Resolution
Audrey Richard, Ian Cherabier, Martin R. Oswald +3
We present a super-resolution method capable of creating a high-resolution texture map for a virtual 3D object from a set of lower-resolution images of that object. Our architectur…
RoutedFusion: Learning Real-time Depth Map Fusion
Silvan Weder, Johannes L. Schönberger, Marc Pollefeys +1
The efficient fusion of depth maps is a key part of most state-of-the-art 3D reconstruction methods. Besides requiring high accuracy, these depth fusion methods need to be scalable…