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.

168,657 papers · 148 categories

Trend · papers per month

3747481,1221,496 · Jun 202019922001200920172026
48 results for image diffusion models

New method tackles video inverse problems using image diffusion models.

problem Spatio-temporal degradation in video inverse problems.
method Leverages image diffusion models to treat time dimension as batch dimension, introduces batch-consistent diffusion sampling.
result Achieves state-of-the-art reconstructions for various spatio-temporal degradations.

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.

DreamFusion uses text-to-image diffusion models to create 3D images efficiently.

problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.

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.

Boomerang generates nonidentical images similar to input on image manifolds.

problem Generating nonidentical images similar to input on image manifolds.
method Adding noise to input image, moving closer to latent space, and mapping back through partial reverse diffusion.
result Boomerang generates nonidentical images similar to input on image manifolds.

DEUA detects diffusion-generated images by accounting for different types of uncertainty.

problem Detecting generated images with varying aleatoric and epistemic uncertainty.
method DEUA framework using Laplace approximation for DEU estimation and asymmetric loss function.
result DEUA achieves state-of-the-art performance on large-scale benchmarks.

Theoretical justification for image inpainting using diffusion models.

problem Improving sample recovery in image inpainting without retraining.
method Analysis of RePaint algorithm and proposing RePaint+^+ to correct misalignment.
result RePaint+^+ algorithm provably recovers the true sample with linear convergence.

A new method for image translation using disentangled style and content preservation.

problem Difficulty in maintaining original content during reverse diffusion in diffusion-based image translation.
method Disentangled style and content representation using intermediate keys from ViT model, CLIP loss, semantic divergence loss, and resampling strategy.
result Outperforms state-of-the-art models in text-guided and image-guided translation tasks.

DiffDenoise preserves fine structures in medical images using conditional diffusion models.

problem Medical image denoising often results in loss of fine structures.
method Conditional diffusion model with stabilized reverse sampling and supervised training.
result DiffDenoise outperforms state-of-the-art methods in medical image denoising.

This paper uses diffusion models for lossy image compression, improving perceptual metrics and practicality.

problem Lossy image compression with improved perceptual metrics and practicality.
method End-to-end optimized lossy image compression using conditional diffusion models.
result The model yields stronger FID scores and competitive performance in distortion metrics.

New diffusion models improve counterfactual image generation with semantic control.

problem Challenges in preserving identity, maintaining quality, and ensuring causal model faithfulness in counterfactual image generation.
method Integrates semantic representations into diffusion models through Pearlian causality, introducing spatial, semantic, and dynamic abduction.
result Demonstrates high-level semantic identity preservation and principled trade-offs between faithful causal control and identity preservation.

Diffusion models reveal a phase transition in reconstructing high-level features.

problem Understanding the hierarchical structure of natural data.
method Study of hierarchical generative models of data using diffusion models.
result The backward diffusion process shows a phase transition at a threshold time, where high-level features suddenly drop in reconstructibility.

Improved image compression with diffusion models outperforming state-of-the-art methods.

problem Difficulties in replicating text-to-image success in image compression.
method Two-stage approach combining autoencoder targeting MSE followed by score-based decoder.
result Significantly improved perceptual quality at a given bit-rate, measured by FID score.

A method merges two pretrained diffusion experts to improve image quality and likelihood.

problem Trade-off between image quality and data likelihood in diffusion models.
method Combining two pretrained diffusion experts by switching between them along the denoising trajectory.
result The merged model consistently matches or outperforms its base components, improving or preserving both likelihood and sample quality.

Pixel-space diffusion models outperform latent models on high-resolution image synthesis.

problem Efficiency and quality trade-off in high-resolution image synthesis.
method Sigmoid loss-weighting, simplified architecture, and resolution scaling.
result Achieved 1.5 FID on ImageNet512, new SOTA results on other datasets.

Variational approach improves diffusion models for solving inverse problems.

problem Challenges in solving inverse problems with diffusion models due to the nonlinear and iterative nature of the diffusion process.
method Proposes a variational approach to approximate the posterior distribution, leading to regularization by denoising diffusion process (RED-Diff).
result Demonstrates improved performance in image restoration tasks compared to state-of-the-art sampling-based diffusion models.

New method solves blind inverse problems by optimizing both operator and image parameters.

problem Solving blind inverse problems with known forward operator.
method Parallel reverse diffusion guided by gradients from intermediate stages.
result State-of-the-art performance on blind deblurring and imaging through turbulence.

New method reduces memorization in diffusion models without sacrificing image quality.

problem Diffusion models often memorize training data, especially with small datasets.
method Train models using noisy data at large noise scales to reduce memorization.
result Significant reduction in memorization without compromising image quality.

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.

High-quality image synthesis with diffusion models, achieving state-of-the-art FID score.

problem Generating high-quality images from latent variables.
method Training diffusion probabilistic models with a weighted variational bound, inspired by denoising score matching and Langevin dynamics.
result State-of-the-art FID score of 3.17 on CIFAR10 dataset.

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.

Remasking improves the quality of discrete diffusion models for natural language and image generation.

problem Limited iterative refinement in masked discrete diffusion models.
method Introducing ReMDM sampler that allows remasking during inference.
result Remasking enables better quality outputs with increased sampling steps.

Develops a robust method for image reconstruction from limited data.

problem Inference of unknown images from few measurements, often ill-posed.
method Introduces DPnP, a diffusion plug-and-play method combining likelihood and score-based samplers.
result Establishes performance guarantees for DPnP, demonstrating robustness and efficiency.

Method generates anatomically-controllable medical images with segmentation guidance.

problem Challenging to enforce anatomical constraints in generated medical images.
method Segmentation-guided diffusion models with random mask ablation training.
result New state-of-the-art in faithfulness to input anatomical masks.

WS diffusion models handle anisotropic Gaussian noise better than conventional methods.

problem Handling anisotropic Gaussian noise in imaging inverse problems.
method Whitened Score (WS) diffusion models based on stochastic differential equations.
result WS DMs outperform conventional DMs on anisotropic Gaussian noise.

CCDF reduces diffusion sampling steps for inverse problems.

problem Slow sampling from diffusion models in inverse problems.
method Starting from a single forward diffusion step with better initialization, followed by stochastic contraction.
result Significantly reduced sampling steps for state-of-the-art reconstruction.

VISION-XL improves HD video quality using latent image diffusion models.

problem Improving high-definition video quality and resolution.
method Latent image diffusion models and pseudo-batch consistent sampling.
result State-of-the-art video reconstruction across various inverse problems.

A smaller, less-trained model guides image generation, improving quality without sacrificing variation.

problem Improving image quality and variation in diffusion models without compromising one for the other.
method Guiding a conditional model with a smaller, less-trained version of the same model.
result Significant improvements in ImageNet generation, setting record FIDs.

Persistently trained EBMs generate images and estimate complex densities.

problem Challenges in ML learning for energy-based models, especially non-convergence of MCMC.
method Introduce diffusion data, learn a joint EBM through persistent training with enhanced sampling.
result First simultaneous achievement of stability, post-training image generation, and superior out-of-distribution detection for image data.