Evaluating Autoencoders for Parametric and Invertible Multidimensional Projections

• URL: http://arxiv.org/abs/2504.16831v1
• Date: Wed, 23 Apr 2025 15:47:20 GMT
• Title: Evaluating Autoencoders for Parametric and Invertible Multidimensional Projections
• Authors: Frederik L. Dennig, Nina Geyer, Daniela Blumberg, Yannick Metz, Daniel A. Keim,
• Abstract summary: We evaluate three autoencoder architectures for creating parametric and invertible projections.<n>Based on a given projection, we train AEs to learn a mapping into 2D space and an inverse mapping into the original space.<n>Our results indicate that AEs with a customized loss function can create smoother parametric and inverse projections than feed-forward neural networks.
• Score: 5.605792949080119
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, neural networks have gained attention for creating parametric and invertible multidimensional data projections. Parametric projections allow for embedding previously unseen data without recomputing the projection as a whole, while invertible projections enable the generation of new data points. However, these properties have never been explored simultaneously for arbitrary projection methods. We evaluate three autoencoder (AE) architectures for creating parametric and invertible projections. Based on a given projection, we train AEs to learn a mapping into 2D space and an inverse mapping into the original space. We perform a quantitative and qualitative comparison on four datasets of varying dimensionality and pattern complexity using t-SNE. Our results indicate that AEs with a customized loss function can create smoother parametric and inverse projections than feed-forward neural networks while giving users control over the strength of the smoothing effect.

Related papers

• DE-VAE: Revealing Uncertainty in Parametric and Inverse Projections with Variational Autoencoders using Differential Entropy [7.23728913278294]
  We propose DE-VAE, an uncertainty-aware variational AE to improve the learned parametric and invertible projections.<n>Given a fixed projection, we train DE-VAE to learn a mapping into 2D space and an inverse mapping back to the original space.<n>Our findings show that DE-VAE can create parametric and inverse projections with comparable accuracy to other current AE-based approaches.
  arXiv  Detail & Related papers  (2025-08-16T19:41:57Z)
• PointVDP: Learning View-Dependent Projection by Fireworks Rays for 3D Point Cloud Segmentation [66.00721801098574]
  We propose view-dependent projection (VDP) to facilitate point cloud segmentation.<n>VDP generates data-driven projections from 3D point distributions.<n>We construct color regularization to optimize the framework.
  arXiv  Detail & Related papers  (2025-07-09T07:44:00Z)
• Distributed Stochastic Optimization of a Neural Representation Network for Time-Space Tomography Reconstruction [4.689071714940848]
  4D time-space reconstruction of dynamic events or deforming objects using X-ray computed tomography (CT) is an important inverse problem in non-destructive evaluation. We propose to perform a 4D time-space reconstruction using a distributed implicit neural representation (DINR) network that is trained using a novel distributed training algorithm.
  arXiv  Detail & Related papers  (2024-04-29T19:41:51Z)
• ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds [52.03819676074455]
  ParaPoint is an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization. This work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
  arXiv  Detail & Related papers  (2024-03-15T14:35:05Z)
• Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering [35.69582529609475]
  This paper introduces a novel neural algorithm for parameterizing neural implicit surfaces to simple parametric domains like spheres and polycubes. It computes bi-directional deformation between the object and the domain using a forward mapping from the object's zero level set and an inverse deformation for backward mapping. We demonstrate the method's effectiveness on images of human heads and man-made objects.
  arXiv  Detail & Related papers  (2023-10-09T08:42:40Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's Eye View [44.78243406441798]
  This paper focuses on leveraging geometry information, such as depth, to model such feature transformation. We first lift the 2D image features to the 3D space defined for the ego vehicle via a predicted parametric depth distribution for each pixel in each view. We then aggregate the 3D feature volume based on the 3D space occupancy derived from depth to the BEV frame.
  arXiv  Detail & Related papers  (2023-07-09T06:07:22Z)
• VTAE: Variational Transformer Autoencoder with Manifolds Learning [144.0546653941249]
  Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables. The nonlinearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. We show that geodesics and accurate computation can substantially improve the performance of deep generative models.
  arXiv  Detail & Related papers  (2023-04-03T13:13:19Z)
• Oracle-Preserving Latent Flows [58.720142291102135]
  We develop a methodology for the simultaneous discovery of multiple nontrivial continuous symmetries across an entire labelled dataset. The symmetry transformations and the corresponding generators are modeled with fully connected neural networks trained with a specially constructed loss function. The two new elements in this work are the use of a reduced-dimensionality latent space and the generalization to transformations invariant with respect to high-dimensional oracles.
  arXiv  Detail & Related papers  (2023-02-02T00:13:32Z)
• Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics [7.507853813361308]
  We introduce a multi-modal technique that leverages 3D point clouds and 2D colour images obtained from LiDAR and camera sensors for surface normal estimation.<n>We present a novel transformer-based neural network architecture that proficiently fuses visual semantic and 3D geometric information.<n>It has been verified that the proposed model can learn from a simulated 3D environment that mimics a traffic scene.
  arXiv  Detail & Related papers  (2022-11-19T03:55:09Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• UnProjection: Leveraging Inverse-Projections for Visual Analytics of High-Dimensional Data [63.74032987144699]
  We present NNInv, a deep learning technique with the ability to approximate the inverse of any projection or mapping. NNInv learns to reconstruct high-dimensional data from any arbitrary point on a 2D projection space, giving users the ability to interact with the learned high-dimensional representation in a visual analytics system.
  arXiv  Detail & Related papers  (2021-11-02T17:11:57Z)
• Ellipse Regression with Predicted Uncertainties for Accurate Multi-View 3D Object Estimation [26.930403135038475]
  This work considers objects whose three-dimensional models can be represented as ellipsoids. We present a variant of Mask R-CNN for estimating the parameters of ellipsoidal objects by segmenting each object and accurately regressing the parameters of projection ellipses.
  arXiv  Detail & Related papers  (2020-12-27T19:52:58Z)
• LodoNet: A Deep Neural Network with 2D Keypoint Matchingfor 3D LiDAR Odometry Estimation [22.664095688406412]
  We propose to transfer the LiDAR frames to image space and reformulate the problem as image feature extraction. With the help of scale-invariant feature transform (SIFT) for feature extraction, we are able to generate matched keypoint pairs (MKPs) A convolutional neural network pipeline is designed for LiDAR odometry estimation by extracted MKPs. The proposed scheme, namely LodoNet, is then evaluated in the KITTI odometry estimation benchmark, achieving on par with or even better results than the state-of-the-art.
  arXiv  Detail & Related papers  (2020-09-01T01:09:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.