In this paper, we propose an end-to-end learnable approach that detects static urban objects from multiple views, re-identifies instances, and finally assigns a geographic position per object.
Recently, probabilistic denoising diffusion models (DDMs) have greatly advanced the generative power of neural networks.
With the release of BiasBed, we hope to foster a common understanding of consistent and meaningful comparisons, and consequently faster progress towards learning methods free of texture bias.
no code implementations • 13 Jun 2022 • Nikolai Kalischek, Nico Lang, Cécile Renier, Rodrigo Caye Daudt, Thomas Addoah, William Thompson, Wilma J. Blaser-Hart, Rachael Garrett, Konrad Schindler, Jan D. Wegner
C\^ote d'Ivoire and Ghana, the world's largest producers of cocoa, account for two thirds of the global cocoa production.
The illustrations contained in field guides deliberately focus on discriminative properties of a species, and can serve as side information to transfer knowledge from seen to unseen classes.
With the decision to employ the source as a constraint rather than only as an input to the prediction, our method differs from state-of-the-art deep architectures for guided super-resolution, which produce targets that, when downsampled, will only approximately reproduce the source.
Automatic identification of plant specimens from amateur photographs could improve species range maps, thus supporting ecosystems research as well as conservation efforts.
To that end, we propose a new, active deep learning method to estimate oil palm density at large scale from Sentinel-2 satellite images, and apply it to generate complete maps for Malaysia and Indonesia.
In this paper we propose an end-to-end learnable approach that detects static urban objects from multiple views, re-identifies instances, and finally assigns a geographic position per object.
We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection.
Our approach is sensor- and sceneagnostic because of SDV, LRF and learning highly descriptive features with fully convolutional layers.
Ranked #4 on Point Cloud Registration on ETH (trained on 3DMatch)
While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data.
We present a method to jointly refine the geometry and semantic segmentation of 3D surface meshes.
With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks.
We propose an adaptive multi-resolution formulation of semantic 3D reconstruction.
The main technical challenge is combining test time information from multiple views of each geographic location (e. g., aerial and street views).
We describe an effective and efficient method for point-wise semantic classification of 3D point clouds.
Ranked #17 on Semantic Segmentation on Semantic3D