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.

169,341 papers · 148 categories

Trend · papers per month

3717411,1121,482 · Jun 202019922001200920182026
48 results for Image Modeling

Generative Adversarial Networks optimize model parameters for image matching.

problem Optimizing model parameters for accurate image matching.
method Model-Assisted Generative Adversarial Network (GAN) to produce fake images matching true images.
result Best match model parameter values can minimize bias in image recognition.

Latent feature models are attractive for image modeling, since images generally contain multiple objects. However, many latent feature models ignore that objects can appear at different locations or require pre-segmentation of images. While the transformed Indian buffet process (tIBP) provides a method for modeling tra…

2012-06-27abs ↗pdf ↗

Paper proposes a CNN-LSTM model for image denoising and reconstruction.

problem Challenging task of image denoising and reconstruction in computer vision.
method Proposes an encoder-decoder model with direct attention, using CNN for encoding and LSTM for decoding.
result Model can reconstruct clean images from highly corrupted ones, even when human understanding is difficult.

New model improves image captioning's ability to describe unseen concepts.

problem Image captioning models struggle with describing unseen combinations of concepts.
method Proposes a multi-task model combining caption generation and image-sentence ranking, with a decoding mechanism to re-rank captions based on image similarity.
result The model significantly outperforms state-of-the-art models in compositional generalization.

Develops statistical guarantees for image-to-image regression models.

problem Current image-to-image regression models lack statistical guarantees for model mistakes and hallucinations.
method Uncertainty quantification techniques with rigorous statistical guarantees for image-to-image regression problems.
result Derives uncertainty intervals around each pixel with formal mathematical guarantees.

Two-layer model sparsifies image residuals for CT image reconstruction.

problem Image reconstruction from limited and corrupted data.
method Pre-learning a two-layer sparsifying transform model with block coordinate descent optimization.
result Preliminary experiments show the two-layer model improves CT image reconstruction from low-dose measurements.

StrokeCoder uses Transformers to generate images from single examples.

problem Creating diverse images from a single example.
method Transformer Neural Network learns from a single path-based example to generate a set of images.
result The model can generate a large set of deviated images that still represent the original image's style and concept.

Proposes a model to generate 3D-aware images from 2D images.

problem Generating 3D-aware images from 2D images.
method Likelihood-based top-down model using Neural Radiance Fields and energy-based latent variables.
result Model can infer 3D object structures from 2D images and generate novel views.

This paper tackles generating manifold-valued images using WGAN.

problem Generating manifold-valued images over natural images.
method Formulated a theorem of optimal transport for Wasserstein distance on manifolds, introduced a new WGAN framework.
result Proposed model generates more plausible manifold-valued images than competitors.

Improved image translation using asymmetric gradient guidance.

problem Trade-off between style transformation and content preservation in diffusion models.
method Asymmetric gradient guidance to guide reverse diffusion sampling.
result Our method outperforms state-of-the-art models in image translation tasks.

Generates coherent storybooks from plain text using diffusion models.

problem Ensuring coherency in a sequence of images for storytelling applications.
method Combines pre-trained LLM and text-guided Latent Diffusion Model for zero-shot generation.
result Outperforms state-of-the-art image editing baselines in generating coherent storybooks.

Generative model uses captions to generate images, improving semantic understanding.

problem Complex image generation models require large datasets and intricate learning.
method Adapts captioning models to generate images, using learned sentence and frame vectors.
result Images generated from multiple captions better capture semantic meaning.

InVA models image outcomes from multiple modalities, outperforming standard VAEs.

problem Understanding relationships across multiple imaging modalities in neuroimaging.
method Integrative Variational Autoencoder (InVA) framework for image-on-image regression.
result InVA accurately predicts PET scans from structural MRI, outperforming conventional models.

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.

Generative models improve image probability estimation but lack interpretability.

problem Lack of interpretability in generative models for natural image distributions.
method Extracted explicit probability density estimates from GANs and analyzed latent representations.
result Natural image density functions are difficult to interpret.

Framework generates realistic crop images for growth modeling.

problem Modeling crop growth over time with precision and detail.
method Two-stage framework: image prediction and growth estimation models.
result Framework accurately predicts crop images with varying conditions.

Gaudy images help train deep neural networks with less data.

problem Training deep neural networks with limited real data from visual cortex neurons.
method Used high-contrast binarized natural images (gaudy images) to train DNNs.
result Reduced training data needed for accurate DNN predictions of visual cortex neuron responses.

Self-guidance controls image generation by extracting properties from diffusion model representations.

problem Generating images from text descriptions is challenging due to the complexity of visual details.
method Self-guidance uses internal representations of diffusion models to control image generation.
result Properties like object shape, location, and appearance can be extracted and used to steer image generation.

Modeling the distribution of natural images is challenging, partly because of strong statistical dependencies which can extend over hundreds of pixels. Recurrent neural networks have been successful in capturing long-range dependencies in a number of problems but only recently have found their way into generative image…

2015-06-10abs ↗pdf ↗

HW2MP-GAN tackles ancient handwritten text recognition.

problem Automatic text recognition from ancient handwritten records.
method Conditional Generative Adversarial Network (HW2MP-GAN) with Sliced Wasserstein distance and U-Net architectures.
result HW2MP-GAN outperforms state-of-the-art models in image-to-image translation and handwritten recognition.

Paper proposes efficient method for evaluating Bayesian models in imaging.

problem Evaluation of Bayesian models in imaging when ground truth is unavailable.
method Novel combination of Bayesian cross-validation and data fission for unsupervised model selection and misspecification detection.
result Achieved excellent selection and detection accuracy with low computational cost.

Generative models solve medical imaging inverse problems without needing paired data.

problem Reconstructing medical images from partial measurements.
method Score-based generative models trained on medical images, then sampling to reconstruct images consistent with measurements and physical model.
result Comparable or better performance in CT and MRI tasks, with improved generalization to unknown measurement processes.

This paper tackles blind image denoising with unknown noise models.

problem Real noisy images have complex noise models that are unknown beforehand.
method Proposes a novel Bayesian nonparametric prior called Dependent Dirichlet Process Tree to model the noise and a variational inference algorithm to recover clean patches.
result Achieves better performance compared to previous approaches on synthesis and real noisy images.

Zero-shot contrastive loss improves text-guided image style transfer without extra training.

problem Stochastic nature of diffusion models leads to trade-offs between style transformation and content preservation.
method Proposes a zero-shot contrastive loss for diffusion models that doesn't require additional fine-tuning or auxiliary networks.
result Method outperforms existing methods while preserving content and requiring no additional training.

A new method improves robustness in image translation by modeling uncertainty.

problem Performance degradation in image translation models due to lack of robustness to outliers and uncertainty.
method UGAC method based on Uncertainty-aware Generalized Adaptive Cycle Consistency, modeling per-pixel residual with generalized Gaussian distribution.
result Our method exhibits stronger robustness towards unseen perturbations in test data.

Unified model for image-to-image translation explained with new geometrical perspective.

problem Lack of solid theoretical interpretations for image-to-image translation models.
method Reformulated adversarial learning model from a geometrical perspective and extended generalization definition.
result Derived a condition to control the generalization capability of the model.

ProAGAN stabilizes GANs for learning SOMs from noisy medical imaging data.

problem Learning stochastic object models from noisy and indirect medical imaging measurements.
method Developed Progressive Growing of AmbientGANs (ProAGAN) to stabilize GANs training.
result Signal detection performance improved using ProAGAN-generated images.

Develops a variational autoencoder for image, label, and caption modeling.

problem Deep learning of images, labels, and captions.
method Uses a Deep Generative Deconvolutional Network (DGDN) and a Convolutional Neural Network (CNN) for image and latent feature encoding.
result Able to predict labels or captions for new images using latent code distributions.