Tag
This paper introduces an iterative refinement framework for data assimilation that combines neural operators and diffusion models to super-resolve multiscale physical systems, outperforming baselines on benchmarks like Kraichnan turbulence.
The paper proposes BaguanHR, a framework that uses variable-wise super-resolution to synthesize high-resolution weather data from coarse-resolution sources, overcoming data limitations for ML-based forecasting and demonstrating power-law scaling effects for improved performance.
RECAST is a machine-learning framework that combines learned correction and super-resolution to restore accuracy in coarse-grid PDE solvers, reducing error by 50-92% across six 1D PDE systems and enabling coarser simulations without losing fidelity.
Introduces ZUNA1.1, a 380M-parameter diffusion autoencoder for flexible EEG signal reconstruction, capable of handling variable-length sequences, arbitrary channels, and temporal intervals, while outperforming standard interpolation methods. The model is released open source under the Apache 2.0 license.
A tweet thread advocating for wider adoption of the HDiT architecture and NATTEN, highlighting its significant speed improvements in super-resolution, image restoration, and genome labeling.
This paper proposes PhyMRI-SR, a physics-aware MRI super-resolution method that uses Gaussian splatting and physics-constrained modeling to dynamically adapt resolution-SNR configurations, achieving state-of-the-art performance.
MrFlow is a training-free multi-resolution acceleration strategy for flow-matching text-to-image models that combines low-resolution generation with pixel-space super-resolution and noise injection, achieving up to 25x end-to-end speedup without training or runtime modifications.
Patch-PODiff-ViT introduces a structured latent diffusion framework using patchwise Proper Orthogonal Decomposition (POD) for super-resolution and uncertainty quantification, enabling efficient diffusion with a fixed linear orthonormal basis and analytic propagation of predictive variance.
This paper introduces a new task, reference-guided generated content super-resolution-refinement (RefGC-SR²), which simultaneously recovers high-resolution details and refines generative artifacts using a frequency-aware diffusion transformer model. The method leverages a high-resolution reference image to improve the quality of AI-generated images during post-processing.
This paper proposes SRT (Super-Resolution for Time Series), a framework that reconstructs high-resolution temporal patterns from low-resolution inputs using a disentangled rectified flow approach. The method decomposes input into trend and seasonal components, applies implicit neural representation for resolution alignment, and introduces cross-resolution attention to generate fine-grained details, achieving state-of-the-art performance on multiple datasets.
AirCast-SR is a diffusion-based foundation model that downscales global AI weather forecasts from 0.25° to 1 km resolution at hourly cadence, producing 67-hour forecasts with near-zero bias and structural realism, while running inference in minutes on a single commodity GPU.
The article presents MOSAIC, a multimodal adaptive optical microscope capable of switching between various imaging modalities (widefield, light-sheet, two-photon, etc.) and applying adaptive correction for sample-induced aberrations, enabling imaging from single molecules to whole organisms in vivo.
Introduces Q-srdrn, a multi-quantile super-resolution network using pinball loss to improve extreme precipitation downscaling, achieving dramatic detection rate gains for heavy rainfall events while maintaining overall accuracy.
Wink Engineering evaluates the efficacy of neural super-resolution as a pre-filter for license plate OCR, concluding that it fails to improve accuracy and often leads to hallucinated characters compared to training directly on low-resolution data.
NVIDIA releases PiD (Pixel Diffusion Decoder), a conditional pixel-space diffusion model that unifies latent-to-pixel decoding and upsampling into one generative module, producing super-resolved images in one pass. Model checkpoints and VAE weights are released under a non-commercial license.
JoyFox Lab releases LTX2.3-ICEdit-Insight, a task-aware video restoration and editing model family built on LTX-2.3, supporting video restoration, HD enhancement, watermark removal, and subtitle removal.