Pith. sign in

REVIEW 8 cited by

LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration

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 2410.15385 v2 pith:D74YFFNT submitted 2024-10-20 cs.CV

Yuang Ai , Huaibo Huang , Ran He This is my paper · ORCID
classification cs.CV
keywords lora-irlow-rankrestorationall-in-oneexpertsimagepre-trainedcomplex
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Prompt-based all-in-one image restoration (IR) frameworks have achieved remarkable performance by incorporating degradation-specific information into prompt modules. Nevertheless, handling the complex and diverse degradations encountered in real-world scenarios remains a significant challenge. To tackle this, we propose LoRA-IR, a flexible framework that dynamically leverages compact low-rank experts to facilitate efficient all-in-one image restoration. Specifically, LoRA-IR consists of two training stages: degradation-guided pre-training and parameter-efficient fine-tuning. In the pre-training stage, we enhance the pre-trained CLIP model by introducing a simple mechanism that scales it to higher resolutions, allowing us to extract robust degradation representations that adaptively guide the IR network. In the fine-tuning stage, we refine the pre-trained IR network through low-rank adaptation (LoRA). Built upon a Mixture-of-Experts (MoE) architecture, LoRA-IR dynamically integrates multiple low-rank restoration experts through a degradation-guided router. This dynamic integration mechanism significantly enhances our model's adaptability to diverse and unknown degradations in complex real-world scenarios. Extensive experiments demonstrate that LoRA-IR achieves SOTA performance across 14 IR tasks and 29 benchmarks, while maintaining computational efficiency. Code and pre-trained models will be available at: https://github.com/shallowdream204/LoRA-IR.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A single 3.6M-parameter model, MoCRA, restores haze, rain, noise, and low light at native 4K in 0.48 seconds per frame, besting eleven retrained baselines on the mean PSNR of the authors' new UHV-4K-AIO benchmark.

  2. CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration

    cs.CV 2026-07 conditional novelty 6.0 of 10

    CoRE-UIR achieves state-of-the-art all-in-one remote sensing image restoration with a common dense expert plus low-rank routed residual experts, improving PSNR by 1.05 dB over BaryIR at 11.83x lower latency.

  3. 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.

  4. GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    GaRA-SAM improves SAM's robustness to image corruption by using input-dependent gating to adjust the effective rank of low-rank adapters, beating prior methods on robust segmentation benchmarks.

  5. BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image Restoration

    cs.CV 2025-05 conditional novelty 6.0 of 10

    BaryIR learns a continuous OT barycenter representation that separates degradation-agnostic from degradation-specific features, improving all-in-one image restoration and generalization to unseen corruptions.

  6. HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement

    cs.CV 2025-07 conditional novelty 5.0 of 10

    HVI-CIDNet+ replaces the HSV color plane with polarized hue-saturation coordinates and a learned dark-intensity collapse, then trains a dual-branch transformer-CNN network with CLIP-derived priors for low-light enhancement.

  7. M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration

    cs.CV 2025-06 conditional novelty 5.0 of 10

    M2Restore is a CLIP-guided Mixture-of-Experts Mamba-CNN model that reports state-of-the-art results on the All-weather all-in-one image restoration benchmark.

  8. Diffusion Once and Done: Degradation-Aware LoRA for Efficient All-in-One Image Restoration

    cs.CV 2025-08 unverdicted novelty 4.0 of 10

    Proposes DOD, a one-step Stable Diffusion model for all-in-one image restoration, but the submitted manuscript text is an unrelated software engineering review, leaving the claim unverifiable.

Pith tools