Search Results for author:
Found 11 papers, 6 papers with code
Accelerating hyperbolic t-SNE
The need to understand the structure of hierarchical or high-dimensional data is present in a variety of fields.
RANRAC: Robust Neural Scene Representations via Random Ray Consensus
We demonstrate the compatibility and potential of our solution for both photo-realistic robust multi-view reconstruction from real-world images based on neural radiance fields and for single-shot reconstruction based on light-field networks.
Tuning the perplexity for and computing sampling-based t-SNE embeddings
Further, we show how this approach speeds up the computation and increases the quality of the embeddings.
Template-free Articulated Neural Point Clouds for Reposable View Synthesis
We demonstrate the versatility of our representation on a variety of articulated objects from common datasets and obtain reposable 3D reconstructions without the need of object-specific skeletal templates.
Deep vanishing point detection: Geometric priors make dataset variations vanish
Deep learning has improved vanishing point detection in images.
Incorporating Texture Information into Dimensionality Reduction for High-Dimensional Images
In this paper, we present a method for incorporating spatial neighborhood information into distance-based dimensionality reduction methods, such as t-Distributed Stochastic Neighbor Embedding (t-SNE).
DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
Learning from 3D point-cloud data has rapidly gained momentum, motivated by the success of deep learning on images and the increased availability of 3D~data.
Ranked #6 on
3D Part Segmentation
on ShapeNet-Part
CNNs on Surfaces using Rotation-Equivariant Features
We propose a network architecture for surfaces that consists of vector-valued, rotation-equivariant features.
How to Manipulate CNNs to Make Them Lie: the GradCAM Case
This illustrates that GradCAM cannot explain the decision of every CNN and provides a proof of concept showing that it is possible to obfuscate the inner workings of a CNN.
GPGPU Linear Complexity t-SNE Optimization
The t-distributed Stochastic Neighbor Embedding (tSNE) algorithm has become in recent years one of the most used and insightful techniques for the exploratory data analysis of high-dimensional data.
Approximated and User Steerable tSNE for Progressive Visual Analytics
Progressive Visual Analytics aims at improving the interactivity in existing analytics techniques by means of visualization as well as interaction with intermediate results.
