Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Goldlücke, Bastian"'
Autor:
Scholz, Stefan, Weidmann, Nils B., Steinert-Threlkeld, Zachary C., Keremoğlu, Eda, Goldlücke, Bastian
Treating images as data has become increasingly popular in political science. While existing classifiers for images reach high levels of accuracy, it is difficult to systematically assess the visual features on which they base their classification. T
Externí odkaz:
http://arxiv.org/abs/2407.03786
Neural approaches have shown a significant progress on camera-based reconstruction. But they require either a fairly dense sampling of the viewing sphere, or pre-training on an existing dataset, thereby limiting their generalizability. In contrast, p
Externí odkaz:
http://arxiv.org/abs/2404.00098
Autor:
Waldmann, Urs, Chan, Alex Hoi Hang, Naik, Hemal, Nagy, Máté, Couzin, Iain D., Deussen, Oliver, Goldluecke, Bastian, Kano, Fumihiro
Markerless methods for animal posture tracking have been rapidly developing recently, but frameworks and benchmarks for tracking large animal groups in 3D are still lacking. To overcome this gap in the literature, we present 3D-MuPPET, a framework to
Externí odkaz:
http://arxiv.org/abs/2308.15316
Publikováno v:
32nd British Machine Vision Conference 2021, BMVA Press, 2021
Refraction is a common physical phenomenon and has long been researched in computer vision. Objects imaged through a refractive object appear distorted in the image as a function of the shape of the interface between the media. This hinders many comp
Externí odkaz:
http://arxiv.org/abs/2305.19743
We propose an end-to-end inverse rendering pipeline called SupeRVol that allows us to recover 3D shape and material parameters from a set of color images in a super-resolution manner. To this end, we represent both the bidirectional reflectance distr
Externí odkaz:
http://arxiv.org/abs/2212.04968
In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formalize the requirements for each component. We instantiate our general dif
Externí odkaz:
http://arxiv.org/abs/2204.13845
Autor:
Giebenhain, Simon, Goldlücke, Bastian
This paper introduces Attentive Implicit Representation Networks (AIR-Nets), a simple, but highly effective architecture for 3D reconstruction from point clouds. Since representing 3D shapes in a local and modular fashion increases generalization and
Externí odkaz:
http://arxiv.org/abs/2110.11860
Reconstructing the 3D geometry of an object from an image is a major challenge in computer vision. Recently introduced differentiable renderers can be leveraged to learn the 3D geometry of objects from 2D images, but those approaches require addition
Externí odkaz:
http://arxiv.org/abs/2110.10784
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.