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.

169,181 papers · 148 categories

Trend · papers per month

1223 · Feb 201919922001200920182026
48 results for photometric stereo

New photometric stereo method using dictionary learning for better normal vector reconstruction.

problem Photometric stereo's reliance on diffuse surface model limits its effectiveness for complex reflectance patterns.
method Developed two formulations of dictionary learning for photometric stereo: one for Lambertian and one for non-Lambertian objects.
result State-of-the-art performance compared to existing robust photometric stereo methods on synthetic and real datasets.

Paper presents a method for robust surface reconstruction from noisy gradients using adaptive dictionary learning.

problem Reconstructing surfaces from noisy photometric stereo normal vector maps.
method Adaptive dictionary learning to sparsely represent spatial patches of the surface, enforcing smoothness constraints.
result The method effectively learns the underlying surface structure and is robust to noise.

New method calibrates photometric redshift PDFs more accurately.

problem Inaccurate photometric redshift uncertainties lead to systematic errors.
method Local re-calibration using feature-space regression of Probability Integral Transform (PIT) distributions.
result Calibrated PDFs are more accurate at all locations in feature space.

Deep learning models improve traffic image segmentation accuracy but vary by city and channel.

problem Improving semantic segmentation accuracy for traffic analysis.
method Evaluation of PSPNet and ICNet on Cityscapes and custom urban images.
result Different models have varying accuracy and inference time for different cities and channels.

The Baire metric induces an ultrametric on a dataset and is of linear computational complexity, contrasted with the standard quadratic time agglomerative hierarchical clustering algorithm. We apply the Baire distance to spectrometric and photometric redshifts from the Sloan Digital Sky Survey using, in this work, about…

2011-04-20abs ↗pdf ↗

New algorithms improve robust PCA for vision tasks with heavy-tailed distributions.

problem Challenging non-convex, non-smooth, non-Lipschitz problems in robust PCA.
method Bilinear factor matrix norm minimization models with double nuclear and hybrid norms.
result Our methods yield more accurate solutions than original Schatten quasi-norm minimization.

The Baire metric induces an ultrametric on a dataset and is of linear computational complexity, contrasted with the standard quadratic time agglomerative hierarchical clustering algorithm. In this work we evaluate empirically this new approach to hierarchical clustering. We compare hierarchical clustering based on the …

2011-06-11abs ↗pdf ↗

PICZL improves photometric redshifts for AGN in all-sky surveys.

problem Challenges in accurately computing photo-z for AGN due to interplay of SMBH and host galaxy emissions.
method PICZL uses an ensemble of CNNs with cross-channel integration of image and catalog data, leveraging Gaussian mixture models.
result PICZL achieves a photo-z variance of 4.5% and outlier fraction of 5.6% on a validation sample of 8098 AGN, outperforming previous methods.

Designing a photometric system to best fulfil a set of scientific goals is a complex task, demanding a compromise between conflicting requirements and subject to various constraints. A specific example is the determination of stellar astrophysical parameters (APs) - effective temperature, metallicity etc. - across a wi…

2004-02-25abs ↗pdf ↗

New method separates audio sources without needing known decompositions.

problem Difficulty in training source separation models on real-world mixtures.
method Generates estimated decompositions from stereo mixtures and trains a deep learning model.
result Trained model can separate single-channel audio sources effectively.

The paper introduces tools for nonparametric conditional density estimation in astronomy.

problem Estimating photometric redshifts and likelihood-free cosmological inference with uncertainty quantification.
method Nonparametric conditional density estimation (CDE) tools in Python and R.
result Comprehensive statistical tools and software for CDE in astronomy.

Y-GAN uses multi-camera data to estimate depth maps without expensive hardware.

problem Depth perception for autonomous systems requires accurate 3D spatial information.
method Proposes Y-GAN, a deep convolutional generative adversarial network.
result Y-GAN estimates depth maps from multi-camera stereo images without ground truth data.

This paper explores synthetic data for training networks in stereo and optical flow tasks.

problem Creating accurate training data for stereo and optical flow tasks is challenging.
method Promotes the use of synthetically generated data and evaluates its impact on network performance.
result Synthetically generated data improves network performance and generalization.

Paper proposes a method to learn and exceed expert demonstrations in unknown reward environments.

problem Learning to outperform expert demonstrations in unknown reward environments.
method A novel concurrent reward and action policy learning approach with a stereo utility definition.
result The proposed method can outperform expert demonstrations in various environments.

Tabular foundation models outperform other methods in conditional density estimation across various datasets.

problem Estimating the full conditional distribution of a response given tabular covariates, especially in settings with heteroscedasticity, multimodality, or asymmetric uncertainty.
method Benchmarked three tabular foundation model variants (TabPFN and TabICL) against six CDE baselines on 39 real-world datasets.
result Tabular foundation models achieve the best CDE loss, log-likelihood, and CRPS across all sample sizes, outperforming other methods.

Genetic algorithms optimize neural networks for cosmological data analysis.

problem Inaccurate results from neural networks due to poor hyperparameter selection.
method Used genetic algorithms to optimize hyperparameters of neural networks.
result Genetic algorithms improve neural network performance in cosmological data analysis.

Dual decomposition provides a tractable framework for designing algorithms for finding the most probable (MAP) configuration in graphical models. However, for many real-world inference problems, the typical decomposition has a large integrality gap, due to frustrated cycles. One way to tighten the relaxation is to intr…

2012-10-16abs ↗pdf ↗

Self-supervised method estimates depth from monocular endoscopy videos.

problem Depth estimation from monocular endoscopy data without manual labeling.
method Convolutional neural networks trained with sparse supervision from stereo methods.
result Submillimeter mean residual error in cross-patient CT scans comparison.

We present a large catalog of optically selected galaxy clusters from the application of a new Gaussian Mixture Brightest Cluster Galaxy (GMBCG) algorithm to SDSS Data Release 7 data. The algorithm detects clusters by identifying the red sequence plus Brightest Cluster Galaxy (BCG) feature, which is unique for galaxy c…

2010-10-26abs ↗pdf ↗

Fink AGN classifier achieves high accuracy in classifying active galactic nuclei.

problem Classifying active galactic nuclei from astronomical data.
method Built features from photometric points and color estimation. Used active learning for optimized training sample. Applied traditional machine learning algorithms.
result Achieved 98.0% accuracy in classifying real alerts from ZTF.

Efficiently extracts local features from whole images using CNNs with pooling layers.

problem Efficiently extracting local features from whole images for various tasks.
method A method to compute patch-based local feature descriptors efficiently in presence of pooling and striding layers for whole images at once, applicable to nearly all existing network architectures.
result Our approach significantly speeds up feature extraction from whole images compared to existing methods.

Proposes a method to improve learning when training data is not representative.

problem Improving supervised learning when training data is not representative (covariate shift).
method Conditioning on propensity scores to balance covariates within strata.
result Significantly improved target prediction and AUC (0.958) on supernovae classification challenge.

Proposes hinge-Wasserstein to improve uncertainty estimation in regression tasks.

problem Estimating multimodal aleatoric uncertainty in regression tasks from images.
method Regression-by-classification paradigm with hinge-Wasserstein loss.
result Hinge-Wasserstein loss improves uncertainty estimation on challenging tasks.

daep learns from irregular, multimodal astronomical data.

problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.

We introduce a new GP kernel based on the sinc function for band-limited signals.

problem Designing covariance kernels for band-limited signals.
method Proposes a Gaussian process kernel with a power spectral density modeled by a rectangular function.
result The sinc kernel facilitates efficient signal processing applications like stereo modulation and band-pass filtering.