REVIEW 11 cited by
Prompt-In-Prompt Learning for Universal Image Restoration
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
Image restoration, which aims to retrieve and enhance degraded images, is fundamental across a wide range of applications. While conventional deep learning approaches have notably improved the image quality across various tasks, they still suffer from (i) the high storage cost needed for various task-specific models and (ii) the lack of interactivity and flexibility, hindering their wider application. Drawing inspiration from the pronounced success of prompts in both linguistic and visual domains, we propose novel Prompt-In-Prompt learning for universal image restoration, named PIP. First, we present two novel prompts, a degradation-aware prompt to encode high-level degradation knowledge and a basic restoration prompt to provide essential low-level information. Second, we devise a novel prompt-to-prompt interaction module to fuse these two prompts into a universal restoration prompt. Third, we introduce a selective prompt-to-feature interaction module to modulate the degradation-related feature. By doing so, the resultant PIP works as a plug-and-play module to enhance existing restoration models for universal image restoration. Extensive experimental results demonstrate the superior performance of PIP on multiple restoration tasks, including image denoising, deraining, dehazing, deblurring, and low-light enhancement. Remarkably, PIP is interpretable, flexible, efficient, and easy-to-use, showing promising potential for real-world applications. The code is available at https://github.com/longzilicart/pip_universal.
Forward citations
Cited by 11 Pith papers
-
Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
An MLLM-guided architecture with a mixture of frequency experts and relational alignment loss achieves state-of-the-art all-in-one image restoration, outperforming prior methods by up to 1.35 dB on the CDD11 dataset.
-
DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization
DRNet uses initialization-stage dynamic reparameterization, a guided DRMLP, and a wavelet encoder to deliver efficient all-in-one image restoration across multiple tasks.
-
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
CEA assembles per-token low-rank residual updates via dense affinities over hyper-adapter-generated components to improve all-in-one image restoration on spatially non-uniform degradations.
-
Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement
SEGD decouples infrared degradations via degradation-specific residual modules, an evidential perception network, and structural-entropy path selection to surpass prior all-in-one methods with fewer parameters.
-
QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration
Per-pixel degradation prototypes plus calibrated local-global attention improve all-in-one restoration accuracy on three benchmark suites.
-
Expandable, Compressible, Mineable: Open-World Thermal Image Restoration
ECMRNet is a continual-learning restoration network that decomposes features into isolated groups, expands new groups for novel degradations, prunes via structural entropy, and mines historical components for compound...
-
Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
An MLLM-guided framework with fusion blocks and mixture-of-frequency-experts achieves new state-of-the-art performance on the CDD11 all-in-one restoration benchmark.
-
Robust Adverse Weather Removal via Spectral-based Spatial Grouping
SSGformer, an all-in-one transformer combining Sobel and SVD spectral prompts with mask-based group-wise attention, reports state-of-the-art averages on All-weather and WeatherStream.
-
Grounding Degradations in Natural Language for All-In-One Video Restoration
RONIN distills per-frame language descriptions of video degradations into lightweight input-conditioned prompts, achieving all-in-one video restoration without any text encoder or MLLM at inference and outperforming p...
-
STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection
STAR-IOD applies scale-decoupled topology alignment and K-Means-based pseudo-label refinement to reduce catastrophic forgetting in remote sensing incremental object detection, reporting 1.7% and 2.1% mAP gains on new ...
-
Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning
PNG model learns high-dimensional prompt features to generate realistic noisy sRGB images consistent with input noise distribution without camera metadata.
Discussion (0). Sign in to comment.