REVIEW 34 cited by
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
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
Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators. In this work, we propose the Denoising Diffusion Null-Space Model (DDNM), a novel zero-shot framework for arbitrary linear IR problems, including but not limited to image super-resolution, colorization, inpainting, compressed sensing, and deblurring. DDNM only needs a pre-trained off-the-shelf diffusion model as the generative prior, without any extra training or network modifications. By refining only the null-space contents during the reverse diffusion process, we can yield diverse results satisfying both data consistency and realness. We further propose an enhanced and robust version, dubbed DDNM+, to support noisy restoration and improve restoration quality for hard tasks. Our experiments on several IR tasks reveal that DDNM outperforms other state-of-the-art zero-shot IR methods. We also demonstrate that DDNM+ can solve complex real-world applications, e.g., old photo restoration.
Forward citations
Cited by 34 Pith papers
-
PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction
PolarVSR is the first unified architecture for continuous space-time polarization video reconstruction from DoFP captures, using polarization-aware implicit neural representations, a flow-guided variation loss, and a ...
-
FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows
FlowBender introduces closed-loop training that lets conditional flow models learn correction policies from their own task-specific alignment errors, outperforming supervised and guidance baselines on fidelity and pla...
-
Reflection Separation from a Single Image via Joint Latent Diffusion
A joint latent diffusion model with cross-layer self-attention and disjoint sampling separates reflection and transmission layers from single images more effectively than prior methods on real-world benchmarks.
-
Proximal-Based Generative Modeling for Bayesian Inverse Problems
PGM replaces the intractable likelihood score in diffusion models with a closed-form Moreau score computed via proximal operators, enabling non-asymptotic sampling for inverse problems trained only on prior data.
-
Proximal-Based Generative Modeling for Bayesian Inverse Problems
PGM framework links diffusion to proximal regularization for closed-form Moreau-score sampling in Bayesian inverse problems, learned only from prior samples.
-
Invertible Diffusion for Low-Memory Channel Gain Map Construction in Wireless Communication Networks
InvDiff-CGM uses invertible architectures in diffusion and U-Net plus a multi-scale prior injector to construct CGMs with 85% lower peak training memory and 38.02 dB PSNR on RadioMap3DSeer.
-
Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators
Diff-ANO uses conditional consistency models and adjoint neural operator surrogates to enable fast, high-quality USCT reconstructions under sparse and partial views by replacing slow PDE solvers and enabling few-step ...
-
COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations
COCO-Inpaint supplies a large-scale dataset and evaluation protocol focused on inpainting-based image forgeries to benchmark existing detection methods.
-
Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Flow-matching
A single latent video flow-matching prior over ERA5, guided by sparse real observations, performs filtering, smoothing, and observation-to-forecast without retraining.
-
From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
TF-PRDiT uses a frozen 3D diffusion transformer prior with task-specific forward operators and predictor-corrector sampling to solve X-ray-to-CT reconstruction and other volumetric inverse problems without any retraining.
-
From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
A single frozen 3D diffusion prior, guided at inference by task-specific forward operators, reconstructs CT from 1-12 X-ray views and handles super-resolution, infilling, and deblurring without retraining.
-
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance
Moebius introduces a compressed diffusion inpainting model using Local-λ Mix Interaction blocks and latent-space multi-granularity distillation to reach 10B-level quality with 0.22B parameters.
-
Measurement Geometry and Design for Trustworthy Generative Inverse Problems
Introduces a local measurement-manifold compatibility measure that bounds stable reconstruction error under generative priors and motivates fixed and adaptive acquisition rules.
-
Conservative Flows: A New Paradigm of Generative Models
Conservative flows generate by running probability-preserving stochastic dynamics initialized at data points rather than noise, using corrected Langevin or predictor-corrector mechanisms on top of any pretrained flow ...
-
Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation
PLMD applies a denoising diffusion model to predict labels for unknown map regions, allowing goal localization in unexplored environments by substituting completed labels into existing navigation pipelines.
-
Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees
Error in approximating the tangent conditional score by the unconditional score in diffusion models is bounded by dimension-free conditional mutual information, with a projected-Langevin method outperforming baselines...
-
Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios
A degradation-aware diffusion framework fuses multimodal images under arbitrary degradations by directly regressing the fused image and applying joint degradation-fusion constraints during limited-step sampling.
-
Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models
Under a Gaussian prior assumption, zero-shot diffusion posterior samplers for inverse problems admit closed-form spectral representations that enable a new parameter-selection framework balancing perceptual quality an...
-
Protein Autoregressive Modeling via Multiscale Structure Generation
PAR is a multi-scale autoregressive transformer framework for protein backbone generation that uses coarse-to-fine prediction, noisy context learning, and flow-based decoding to achieve high-quality unconditional and ...
-
Semantic-Guided Cross-Sensor Super Resolution of Remote Sensing Images: A Gated Dual Conditioning Flow Matching Model
A gated dual-conditioning flow-matching model achieves 10 m→2 m cross-sensor super-resolution with a 38% FID reduction over the best baseline on a rare-landform (retrogressive thaw slump) benchmark.
-
NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
NPN introduces a neural-network-based regularization that promotes reconstructions lying in a low-dimensional projection of the sensing operator's null-space, with claimed theoretical guarantees and improved empirical...
-
A novel method and dataset for depth-guided image deblurring from smartphone Lidar
Lidar depth-guided deblurring via a zero-shot diffusion method, evaluated on a new 45-scene dataset, achieves the best perceptual quality (LPIPS).
-
Zero-shot CT Super-Resolution using Diffusion-based 2D Projection Priors and Signed 3D Gaussians
A two-stage zero-shot CT super-resolution framework that upscales 2D X-ray projections with a diffusion prior and reconstructs the 3D volume using negative-density 3D Gaussian splatting.
-
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
A SVD-based, coordinate-wise DDIM sampler is claimed to asymptotically sample from the posterior for noisy linear inverse problems, but the proof's posterior identification step does not follow from the stated updates.
-
Diffusion-Based Noise-Adaptive Null-Space Channel Estimation for OFDM Systems
A diffusion estimator with noise-adaptive null-space correction recovers sparse-pilot OFDM channels at lower NMSE than MMSE, toolbox, DPS, and DMPS baselines on 5G TDL/CDL simulations.
-
Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems
Introduces a cascade-based structural decomposition of posterior uncertainty to isolate intrinsic ambiguity from estimation uncertainty in deep generative models for linear inverse problems.
-
Unifying Deep Stochastic Processes for Image Enhancement
Stochastic image enhancement methods are shown to be variants of a shared SDE differing in drift, diffusion, terminal distributions and boundary conditions, with controlled experiments revealing no single dominant fam...
-
Dual Ascent Diffusion for Inverse Problems
A dual ascent optimization framework is introduced for MAP estimation with diffusion priors, claimed to outperform prior methods on image restoration in quality, noise robustness, speed, and data fidelity.
-
A Survey on Diffusion Models for Inverse Problems
A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.
-
Efficient Difficulty-Aware Dynamic Routing for Diffusion-Based Real-World Image Super-Resolution
DDR-SR routes each real-world low-resolution image to one of two diffusion experts based on a high-frequency-loss difficulty score, using a low-compression VAE for hard images and a high-compression VAE for easy image...
-
Generative Spectrum Cartography: Unified Reconstruction and Active Sensing via Diffusion Models
A diffusion-based framework reconstructs spectrum maps and guides where to sample next using closed-form Bayesian updates for linear and quantized measurements.
-
Local MAP Sampling for Diffusion Models
LMAPS frames reverse-diffusion inverse-problem solving as repeated local MAP estimation, unifying existing optimization-based solvers, and achieves strong PSNR gains on tasks like motion deblurring, JPEG restoration, ...
-
InfraDiffusion: zero-shot depth map restoration with diffusion models and prompted segmentation from sparse infrastructure point clouds
InfraDiffusion adapts DDNM with boundary masks to restore depth maps from masonry point clouds, reporting large SAM-based brick-segmentation improvements, but the evaluation protocol appears to ground the masks in the...
-
Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projection
A linear average of GAP and HQS data-consistency updates during DDIM sampling is proposed, but it reduces to a single scaled projection when the sensing matrix is orthogonal.
Discussion (0). Sign in to comment.