Pith. sign in

REVIEW 11 cited by

Image Restoration with Mean-Reverting Stochastic Differential Equations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2301.11699 v3 pith:UL4A4DEW submitted 2023-01-27 cs.LG cs.CV

Ziwei Luo , Fredrik K. Gustafsson , Zheng Zhao , Jens Sjölund , Thomas B. Schön This is my paper · ORCID
classification cs.LGcs.CV
keywords imagemean-revertingrestorationapproachderainingdifferentiallearnproposed
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents a stochastic differential equation (SDE) approach for general-purpose image restoration. The key construction consists in a mean-reverting SDE that transforms a high-quality image into a degraded counterpart as a mean state with fixed Gaussian noise. Then, by simulating the corresponding reverse-time SDE, we are able to restore the origin of the low-quality image without relying on any task-specific prior knowledge. Crucially, the proposed mean-reverting SDE has a closed-form solution, allowing us to compute the ground truth time-dependent score and learn it with a neural network. Moreover, we propose a maximum likelihood objective to learn an optimal reverse trajectory that stabilizes the training and improves the restoration results. The experiments show that our proposed method achieves highly competitive performance in quantitative comparisons on image deraining, deblurring, and denoising, setting a new state-of-the-art on two deraining datasets. Finally, the general applicability of our approach is further demonstrated via qualitative results on image super-resolution, inpainting, and dehazing. Code is available at https://github.com/Algolzw/image-restoration-sde.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ScaleResfusion: Residual Rectified Flow based on Residual Vector Field

    cs.CV 2026-07 conditional novelty 6.0 of 10

    ScaleResfusion modifies rectified flow to start from a noisy low-quality image and learn only a residual velocity field, enabling 4-step image restoration with LoRA fine-tuning of billion-scale text-to-image models.

  2. Decoupling Cross-Modality Manifold Discrepancy: Leveraging Visible Diffusion Priors for Infrared Super-Resolution

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Shift-IISR steers a frozen visible-pretrained diffusion model toward the infrared manifold via global representation modulation and local Sobel-edge refinement, improving infrared super-resolution consistency.

  3. Geometric Analysis of Magnetic Labyrinthine Stripe Evolution via Deep Learning Segmentation

    cond-mat.mtrl-sci 2025-09 unverdicted novelty 6.0 of 10

    U-Net segmentation of magneto-optical images combined with skeletonization and graph analysis quantifies the transition from quenched to annealed states in magnetic labyrinthine stripes and identifies two field-polari...

  4. TAP: Parameter-efficient Task-Aware Prompting for Adverse Weather Removal

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A two-stage prompt-tuning method with low-rank and contrastive prompt enhancement claims all-in-one adverse weather removal at 2.75M parameters.

  5. UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A stochastic optimal control formulation of diffusion bridges, where Doob's h-transform is the infinite-penalty limit and a finite penalty yields a tunable detail-preserving bridge.

  6. Degradation-Consistent Learning via Bidirectional Diffusion for Low-Light Image Enhancement

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Training a diffusion model on both enhancement and degradation paths, with a shared encoder and a reflection-aware correction module, yields state-of-the-art low-light enhancement on multiple benchmarks.

  7. DiffNMR3: Advancing NMR Resolution Beyond Instrumental Limits

    physics.ins-det 2025-02 reject novelty 5.0 of 10

    A conditional diffusion model (MSSR) reconstructs high-resolution NMR spectra from Gaussian-blurred low-resolution spectra across multiple upscaling factors, but only synthetic degradation is tested.

  8. Diffusion-Based Limited-Angle CT Reconstruction under Noisy Conditions

    eess.IV 2025-07 conditional novelty 4.0 of 10

    Adding a noise-matched rectification step (RNSD+) to mean-reverting SDE sinogram inpainting improves limited-angle CT reconstruction under 5-15 dB Gaussian noise on the synthetic ChromSTET2025 dataset.

  9. Low-Light Enhancement via Encoder-Decoder Network with Illumination Guidance

    cs.CV 2025-07 conditional novelty 4.0 of 10

    EDNIG, a U-Net with illumination guidance, spatial pyramid pooling, and a GAN-based loss, reports 21.512 dB PSNR and 0.8313 SSIM on the LOL validation set.

  10. Frequency-Domain Fusion Transformer for Image Inpainting

    cs.CV 2025-06 reject novelty 4.0 of 10

    Dabformer combines wavelet and Gabor filtered attention with an FFT gating network, but the reported gains over prior methods are inconsistent across datasets.

  11. Demystifying the Visual Quality Paradox in Multimodal Large Language Models

    cs.CV 2025-06 reject novelty 4.0 of 10

    Multimodal LLM accuracy can improve on visually degraded images, and a lightweight test-time tuning module that modulates input quality yields small accuracy gains on some benchmarks.

Pith tools