REVIEW 7 cited by
Image Super-Resolution via Iterative Refinement
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models to conditional image generation and performs super-resolution through a stochastic denoising process. Inference starts with pure Gaussian noise and iteratively refines the noisy output using a U-Net model trained on denoising at various noise levels. SR3 exhibits strong performance on super-resolution tasks at different magnification factors, on faces and natural images. We conduct human evaluation on a standard 8X face super-resolution task on CelebA-HQ, comparing with SOTA GAN methods. SR3 achieves a fool rate close to 50%, suggesting photo-realistic outputs, while GANs do not exceed a fool rate of 34%. We further show the effectiveness of SR3 in cascaded image generation, where generative models are chained with super-resolution models, yielding a competitive FID score of 11.3 on ImageNet.
Forward citations
Cited by 7 Pith papers
-
Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
DiRIM uses a diffusion model with recurrent score refinement to sample pixel-space joint posteriors of the lensed source and foreground mass map, reproducing mock strong-lens observations to the noise level.
-
SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis
SHARP applies a spectrum-aware dynamic RoPE scaling schedule that promotes resolution more strongly in early denoising stages and relaxes it later, outperforming static baselines on quality metrics for remote sensing images.
-
Mixture-of-Gaussians-Guided Schedule Design for Brownian Bridge Diffusion Models
Under a MoG prior, BBDM reverse dynamics admit tractable selected-label reconstruction laws that yield universal MSE- and Wasserstein-optimal bridge schedules independent of degradation.
-
ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization
Iteratively optimized prompts improve compositional text-to-image scores by up to 20% across three models, and the improved prompts transfer across models.
-
SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models
SuperPure is an iterative GAN-super-resolution masking defense that reports higher robustness than PatchCleanser against localized and distributed adversarial patches at a small fraction of the compute.
-
Astrophotography turbulence mitigation via generative models
AstroDiff improves astronomical image restoration under atmospheric turbulence by fusing a diffusion-based generative prior with a restoration branch via SGLD, achieving lower LPIPS and BRISQUE than prior learning-bas...
-
MODS: Multi-source Observations Conditional Diffusion Model for Meteorological State Downscaling
A multi-source satellite-conditioned diffusion model for ERA5 downscaling reports improved station-level metrics, but the evaluation is compromised because station observations are used as sampling guidance and as the...
Discussion (0). Continue with ORCID to comment.