Fusing the Old with the New: Learning Relative Camera Pose with
Geometry-Guided Uncertainty
- URL: http://arxiv.org/abs/2104.08278v1
- Date: Fri, 16 Apr 2021 17:59:06 GMT
- Title: Fusing the Old with the New: Learning Relative Camera Pose with
Geometry-Guided Uncertainty
- Authors: Bingbing Zhuang, Manmohan Chandraker
- Abstract summary: We present a novel framework that involves probabilistic fusion between the two families of predictions during network training.
Our network features a self-attention graph neural network, which drives the learning by enforcing strong interactions between different correspondences.
We propose motion parmeterizations suitable for learning and show that our method achieves state-of-the-art performance on the challenging DeMoN and ScanNet datasets.
- Score: 91.0564497403256
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Learning methods for relative camera pose estimation have been developed
largely in isolation from classical geometric approaches. The question of how
to integrate predictions from deep neural networks (DNNs) and solutions from
geometric solvers, such as the 5-point algorithm, has as yet remained
under-explored. In this paper, we present a novel framework that involves
probabilistic fusion between the two families of predictions during network
training, with a view to leveraging their complementary benefits in a learnable
way. The fusion is achieved by learning the DNN uncertainty under explicit
guidance by the geometric uncertainty, thereby learning to take into account
the geometric solution in relation to the DNN prediction. Our network features
a self-attention graph neural network, which drives the learning by enforcing
strong interactions between different correspondences and potentially modeling
complex relationships between points. We propose motion parmeterizations
suitable for learning and show that our method achieves state-of-the-art
performance on the challenging DeMoN and ScanNet datasets. While we focus on
relative pose, we envision that our pipeline is broadly applicable for fusing
classical geometry and deep learning.
Related papers
- Unveiling Mode Connectivity in Graph Neural Networks [30.854487554682628]
This work presents the first investigation of mode connectivity in graph neural networks (GNNs)
We uncover that GNNs exhibit distinct non-linear mode connectivity, diverging from patterns observed in fully-connected networks or CNNs.
We establish a link between mode connectivity and generalization, proposing a generalization bound based on loss barriers and revealing its utility as a diagnostic tool.
arXiv Detail & Related papers (2025-02-18T07:46:10Z) - Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks [7.956678963695681]
We explore intersections between sparse coding and deep learning to enhance our understanding of feature extraction capabilities.
We derive convergence rates for convolutional neural networks (CNNs) in their ability to extract sparse features.
Inspired by the strong connection between sparse coding and CNNs, we explore training strategies to encourage neural networks to learn more sparse features.
arXiv Detail & Related papers (2024-08-10T12:43:55Z) - Joint Diffusion Processes as an Inductive Bias in Sheaf Neural Networks [14.224234978509026]
Sheaf Neural Networks (SNNs) naturally extend Graph Neural Networks (GNNs)
We propose two novel sheaf learning approaches that provide a more intuitive understanding of the involved structure maps.
In our evaluation, we show the limitations of the real-world benchmarks used so far on SNNs.
arXiv Detail & Related papers (2024-07-30T07:17:46Z) - ConCerNet: A Contrastive Learning Based Framework for Automated
Conservation Law Discovery and Trustworthy Dynamical System Prediction [82.81767856234956]
This paper proposes a new learning framework named ConCerNet to improve the trustworthiness of the DNN based dynamics modeling.
We show that our method consistently outperforms the baseline neural networks in both coordinate error and conservation metrics.
arXiv Detail & Related papers (2023-02-11T21:07:30Z) - Knowledge Enhanced Neural Networks for relational domains [83.9217787335878]
We focus on a specific method, KENN, a Neural-Symbolic architecture that injects prior logical knowledge into a neural network.
In this paper, we propose an extension of KENN for relational data.
arXiv Detail & Related papers (2022-05-31T13:00:34Z) - Quasi-orthogonality and intrinsic dimensions as measures of learning and
generalisation [55.80128181112308]
We show that dimensionality and quasi-orthogonality of neural networks' feature space may jointly serve as network's performance discriminants.
Our findings suggest important relationships between the networks' final performance and properties of their randomly initialised feature spaces.
arXiv Detail & Related papers (2022-03-30T21:47:32Z) - Neural Networks Enhancement with Logical Knowledge [83.9217787335878]
We propose an extension of KENN for relational data.
The results show that KENN is capable of increasing the performances of the underlying neural network even in the presence relational data.
arXiv Detail & Related papers (2020-09-13T21:12:20Z) - Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
We propose a topological perspective to represent a network into a complete graph for analysis.
By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner.
This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
arXiv Detail & Related papers (2020-08-19T04:53:31Z) - A deep learning framework for solution and discovery in solid mechanics [1.4699455652461721]
We present the application of a class of deep learning, known as Physics Informed Neural Networks (PINN), to learning and discovery in solid mechanics.
We explain how to incorporate the momentum balance and elasticity relations into PINN, and explore in detail the application to linear elasticity.
arXiv Detail & Related papers (2020-02-14T08:24:53Z)
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.