Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Feb 199419922001200920172026
48 results for image completion

LMConv improves autoregressive models for image generation and completion.

problem Limited generation order in autoregressive models restricts their applicability.
method Introduces LMConv, a modified 2D convolution that allows arbitrary masks to be applied to weights.
result LMConv achieves improved performance on image density estimation and coherent completions.

Bayesian model improves image completion accuracy by automatically learning low rank structure.

problem Improving image completion accuracy with limited data and avoiding overfitting.
method Developed a Bayesian low rank tensor ring model with multiplicative interaction and Student-T distribution for sparse core factors.
result The proposed method outperforms state-of-the-art image completion techniques, especially in recovery accuracy.

We study the mean curvature flow of complete space-like submanifolds in pseudo-Euclidean space with bounded Gauss image, as well as that of complete submanifolds in Euclidean space with convex Gauss image. By using the confinable property of the Gauss image under the mean curvature flow we prove the long time existence…

2005-12-15abs ↗pdf ↗

Proposes a new model for image restoration combining deep learning and total variation.

problem Restoring images from limited data with low-rank constraints insufficient.
method Regularized Deep Matrix Factorized (RDMF) model using deep neural network's low-rank bias and total variation.
result Outperforms state-of-the-art models in image restoration from few observations.

We show that under certain symmetry, the images of complete harmonic embeddings from the complex plane into the hyperbolic plane is completely determined by the geometric information of the vertical measured foliation and is independent of the horizontal measured foliation of the corresponding Hopf differentials.

2005-02-24abs ↗pdf ↗

Study complete space-like stationary surfaces with graphical Gauss image, estimating exceptional values and classifying degenerate surfaces.

problem Estimating exceptional values and classifying degenerate surfaces in Minkowski spacetime.
method Generalizing Fujimoto's theorem, estimating upper bounds, introducing conjugate similarity, and establishing structure theorems.
result Sharp contrast to Bernstein type results for minimal surfaces, estimating upper bounds of exceptional values.

Tensor completion estimates missing components by exploiting the low-rank structure of multi-way data. The recently proposed methods based on tensor train (TT) and tensor ring (TR) show better performance in image recovery than classical ones. Compared with TT and TR, the projected entangled pair state (PEPS), which is…

2019-03-12abs ↗pdf ↗

Study on Gauss images of specific minimal surfaces with finite curvature.

problem Characterizing Gauss images of minimal surfaces with finite total curvature.
method Analyzing the number and weight of omitted and totally ramified values of Gauss maps.
result Construction of new minimal surfaces with specific Gauss map properties.

AIR-Net adapts low-rank regularization dynamically for better image completion.

problem Fixed low-rank regularization limits adaptability to different images.
method AIR-Net uses adaptive and implicit regularization parameterized by a dynamic Laplacian matrix.
result AIR-Net enhances implicit regularization and outperforms fixed methods in non-uniform missing data scenarios.

Personalizes query completion in digital commerce with image-based vectors.

problem High bounce rate and low recurring users in query completion.
method Injects dense vectors from product images into a noisy channel model.
result Image-based personalization improves query completion and user experience.

There is growing interest in multi-label image classification due to its critical role in web-based image analytics-based applications, such as large-scale image retrieval and browsing. Matrix completion has recently been introduced as a method for transductive (semi-supervised) multi-label classification, and has seve…

2019-04-08abs ↗pdf ↗

We determine all complete projective special real surfaces. By the supergravity r-map, they give rise to complete projective special Kähler manifolds of dimension 6, which are distinguished by the image of their scalar curvature function. By the supergravity c-map, the latter manifolds define in turn complete quaternio…

2013-02-19abs ↗pdf ↗

Study proves rigidity theorems for ancient solutions to mean curvature flow with convex image.

problem Rigidity of ancient solutions to mean curvature flow with convex Gauss image.
method Refined curvature estimates.
result Better rigidity theorems for ancient solutions in higher codimension.

The paper explores winding numbers of almost embeddings of a 4-vertex graph in the plane.

problem Understanding the winding numbers of almost embeddings of a 4-vertex graph in the plane.
method Constructing examples to show the only relation between the winding numbers of cycles in the graph.
result The sum of winding numbers is odd, and this is the only relation between them.

In this paper we construct a complete injective holomorphic immersion CC2\mathbb{C}\to\mathbb{C}^2 whose image is dense in C2\mathbb{C}^2. The analogous result is obtained for any closed complex submanifold XCnX\subset \mathbb{C}^n for n>1n>1 in place of CC2\mathbb{C}\subset\mathbb{C}^2. We also show that, if XX intersect…

2017-02-26abs ↗pdf ↗

In this paper we consider completed coverings that are branched coverings in the sense of Fox. For completed coverings between PL manifolds we give a characterization of the existence of a monodromy representation and the existence of a locally compact monodromy representation. These results stem from a characterizatio…

2014-06-25abs ↗pdf ↗

Matrix completion is a widely used technique for image inpainting and personalized recommender system, etc. In this work, we focus on accelerating the matrix completion using faster randomized singular value decomposition (rSVD). Firstly, two fast randomized algorithms (rSVD-PI and rSVD- BKI) are proposed for handling …

2018-10-16abs ↗pdf ↗

Point source detection at low signal-to-noise is challenging for astronomical surveys, particularly in radio interferometry images where the noise is correlated. Machine learning is a promising solution, allowing the development of algorithms tailored to specific telescope arrays and science cases. We present DeepSourc…

2018-07-07abs ↗pdf ↗

PAC-Bayesian matrix completion with a spectral scaled Student prior offers efficient inference.

problem Matrix completion with underlying low-rank structure.
method Spectral scaled Student prior and PAC-Bayesian bounds.
result Minimax-optimal oracle inequality for model misspecification and general sampling distribution.

Shallow Art presents, implements, and tests the use of simple single-output classification and regression models for the purpose of art generation. Various machine learning algorithms are trained on collections of computer generated images, artworks from Vincent van Gogh, and artworks from Rembrandt van Rijn. These mod…

2019-10-21abs ↗pdf ↗

In this paper we try to generalize the Haefliger theorem on completly solvable Lie foliations. We prove that: every completely solvable Lie foliation on a compact manifold is the inverse image of a homogenus foliation. Every manifold in this paper is compact and our Lie group G is connexe and simply connexe.

2018-02-22abs ↗pdf ↗

New method estimates neuronal connectivity from partially observed data.

problem Estimating neuronal connectivity from partially observed data.
method Two-step approach: low-rank covariance completion followed by graph structure estimation.
result Graph selection consistency demonstrated for one approach.

This paper tabulates prime knot projections up to eight double points.

problem Tabulating prime knot projections and their mirror images up to a certain number of double points.
method Systematic flypes and enumeration of tangles with at most four double points, using arrow diagrams.
result Complete table of prime knot projections with their mirror images up to eight double points.

Deep-SLR reduces SLR complexity with CNN, enabling efficient parallel MRI.

problem High computational complexity in SLR matrix completion.
method Convolutional Neural Network (CNN) trained to estimate annihilation relations from imperfect k-space measurements.
result Significant reduction in runtime by three orders of magnitude compared to SLR schemes.

Image-to-image networks speed up SAR model parameter estimation.

problem Computational infeasibility of MLE for large, non-stationary spatial fields.
method Used image-to-image networks to estimate SAR model parameters.
result Image-to-image networks enable faster and more accurate parameter estimation.

Stochastic neural ODEs outperform deterministic ones on image classification tasks.

problem Improving generalization in continuous-time models like neural ODEs.
method Empirical study of stochastically regularized neural ODEs using SDEs.
result Data augmentation negates the benefits of stochastic regularization, making neural ODEs and SDEs nearly equivalent.

We study completeness properties of the Sobolev diffeomorphism groups Ds(M)\mathcal D^s(M) endowed with strong right-invariant Riemannian metrics when the underlying manifold MM is Rd\mathbb R^d or compact without boundary. The main result is that for s>dimM/2+1s > \dim M/2 + 1, the group Ds(M)\mathcal D^s(M) is geodesically and me…

2014-03-09abs ↗pdf ↗

Analytic completeness criterion applied to constant mean curvature surfaces.

problem Determining the analytic completeness of constant mean curvature surfaces.
method Defining arc-properness and applying it to surfaces in de Sitter 3-space.
result A criterion for the analytic completeness of G-catenoids and their extensions.

This work provides uncertainty intervals for semantic latent variables in disentangled latent spaces.

problem Challenges in providing meaningful uncertainty quantification for semantic information in disentangled latent spaces.
method Uses quantile regression to output heuristic uncertainty intervals, calibrates these intervals to contain true latent values, and propagates them through the generator.
result Reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in image super-resolution and image completion.

Low-rank tensor completion recovers missing entries based on different tensor decompositions. Due to its outstanding performance in exploiting some higher-order data structure, low rank tensor ring has been applied in tensor completion. To further deal with its sensitivity to sparse component as it does in tensor princ…

2019-03-31abs ↗pdf ↗