Image Restoration
Sharing Key Semantics in Transformer Makes Efficient Image Restoration
·3184 words·15 mins·
loading
·
loading
Computer Vision
Image Restoration
🏢 Peking University
SemanIR boosts image restoration efficiency by cleverly sharing key semantic information within Transformer layers, achieving state-of-the-art results across multiple tasks.
Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
·3390 words·16 mins·
loading
·
loading
Computer Vision
Image Restoration
🏢 Tsinghua University
AdaptIR: A novel parameter-efficient method for generalized image restoration using a heterogeneous Mixture-of-Experts (MoE) architecture that achieves superior performance and generalization.
Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting
·1825 words·9 mins·
loading
·
loading
Computer Vision
Image Restoration
🏢 AIRI
Deep Fourier Shifting boosts small image restoration networks by using an information-lossless Fourier cycling shift operator, improving performance across various low-level tasks while reducing compu…
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
·2906 words·14 mins·
loading
·
loading
Computer Vision
Image Restoration
🏢 Samsung Research
EnsIR: Training-free image restoration ensemble via Gaussian mixture models, boosting accuracy efficiently.
CosAE: Learnable Fourier Series for Image Restoration
·2867 words·14 mins·
loading
·
loading
Computer Vision
Image Restoration
🏢 NVIDIA Research
CosAE: a novel autoencoder using learnable Fourier series achieves state-of-the-art image restoration by encoding frequency coefficients in its narrow bottleneck, preserving fine details even with ext…