Global ETD Search

Geometry Processing with Neural Fields

Yang, GuandaoCornell University2023

… Specifically, each shape is represented by a neural network that takes a spatial coordinate as input and outputs a scalar or vector value. We coin such representation neural fields. Neural field can circumvent the common challenges of meshes and voxels because it doesn’t explicitly discretize …

cornell Repository record for Geometry Processing with Neural Fields (opens in a new tab)

Visual Terrain Relative Navigation: Pose Estimation, Neural Fields, and Verification

Maggio, DominicMassachusetts Institute of Technology2023

… explore the question of whether newly emerging Neural Radiance Fields (NeRF) can be efficiently leveraged as a map for visual localization. We propose a NeRF-based localization pipeline coined Loc-NeRF which uses a particle filter backbone to perform monocular camera pose estimation utilizing …

mit Repository record for Visual Terrain Relative Navigation: Pose Estimation, Neural Fields, and Verification (opens in a new tab)

Combining Masked Autoencoding and Neural Fields for Multi-band Satellite Understanding

Huang, Kuan WeiMassachusetts Institute of Technology2023

… translation tasks. In addition, we show that the neural feature field learned by our method is more effective than baselines for transfer learning to predict Amazon rainforest deforestation.

mit Repository record for Combining Masked Autoencoding and Neural Fields for Multi-band Satellite Understanding (opens in a new tab)

LARGE-SCALE NEURAL 3D SCENE RECONSTRUCTION, RENDERING, AND BEYOND

CHEN YU2025

This thesis advances neural 3D reconstruction into a scalable and robust process for real-world applications. While techniques like NeRF and 3D Gaussian Splatting (3DGS) show promise, they face challenges in scalability, robustness to imperfect camera poses, and consistency across distributed …

nus Repository record for LARGE-SCALE NEURAL 3D SCENE RECONSTRUCTION, RENDERING, AND BEYOND (opens in a new tab)

Neural Networks on Eigenvector Data

Lim, DerekMassachusetts Institute of Technology2023

… In this thesis, we present the first neural networks that process eigenvector input while respecting these symmetries. We build neural networks that are invariant to sign and basis symmetries as well as neural networks that are equivariant to sign symmetries. Under certain conditions, …

mit Repository record for Neural Networks on Eigenvector Data (opens in a new tab)

Continuous dimensional emotion tracking in music

Imbrasaite, VaivaUniversity of Cambridge2015

… work done in musicology, psychology, and other fields. However, automatic emotion prediction in music is still at its infancy and often lacks that transfer of knowledge from the other fields surrounding it. This dissertation explores automatic continuous dimensional emotion prediction in music …

cambridge Repository record for Continuous dimensional emotion tracking in music (opens in a new tab)

On the Interplay of 2D and 3D Representations for Robotic Perception

Milano, FrancescoETH Zurich2025

ethz Repository record for On the Interplay of 2D and 3D Representations for Robotic Perception (opens in a new tab)

Spatio-temporal tomographic imaging

Iskender, BerkUniversity of Illinois at Urbana-Champaign2024

Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms

uiuc Repository record for Spatio-temporal tomographic imaging (opens in a new tab)