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.
Prompt-in-prompt learning for universal image restoration
7 Pith papers cite this work, alongside 6 external citations. Polarity classification is still indexing.
7
Pith papers citing it
6
external citations · external index
citation-role summary
background 3
citation-polarity summary
fields
cs.CV 7years
2026 7verdicts
UNVERDICTED 7roles
background 3polarities
background 3representative citing papers
DRNet uses initialization-stage dynamic reparameterization, a guided DRMLP, and a wavelet encoder to deliver efficient all-in-one image restoration across multiple tasks.
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.
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.
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 degradations in open-world TIR imaging.
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 DIOR-IOD and DOTA-IOD datasets.
PNG model learns high-dimensional prompt features to generate realistic noisy sRGB images consistent with input noise distribution without camera metadata.
citing papers explorer
-
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.
-
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 degradations in open-world TIR imaging.
-
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 DIOR-IOD and DOTA-IOD datasets.
-
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.