Noise-Aware Illumination Interpolator for Unsupervised Low-Light Image Enhancement
A denoising-first and enhancing-later pipeline is proposed to achieve clear visibility in low-light conditions with dynamic noise, leveraging a novel noise estimation method and a learnable illumination interpolator.
Enhancing Image Harmonization with Latent Diffusion Models
A method is proposed to enable pre-trained latent diffusion models to achieve state-of-the-art results on the image harmonization task by addressing the image distortion issue caused by the VAE compression.
Diverse Attention Fusion Restoration Transformer (DART): A Novel Multi-Attention Approach for Efficient Image Restoration
The proposed Diverse Attention Fusion Restoration Transformer (DART) model effectively integrates information from various sources (long sequences, local and global regions, feature dimensions, and positional dimensions) to address complex image restoration challenges, achieving state-of-the-art performance with improved efficiency.
Efficient and High-Performing Image Restoration Network with Low Latency and Memory Consumption
The authors propose GAMA-IR, an image restoration network that achieves state-of-the-art performance while being significantly faster and more memory-efficient than existing methods.
Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution Analysis
Proposing Self-Adaptive Reality-Guided Diffusion (SARGD) for artifact-free super-resolution, enhancing image quality and reducing inference time.
Residual Denoising Diffusion Models: Unified Image Generation and Restoration
Residual Denoising Diffusion Models (RDDM) propose a dual diffusion process to unify image generation and restoration by introducing residuals and noise diffusion.
PQDynamicISP: Dynamically Controlled Image Signal Processor for Perceptual Quality
提案された軽量なISPは、高い画像品質を実現するために動的に制御されるパラメータを組み合わせています。
NTIRE 2023 Image Shadow Removal Challenge Technical Report by Team IIM TTI
ShadowFormerの改善と新しい手法による影の除去方法を提案し、NTIRE2023 Shadow Removal Challengeで高いスコアを達成した。
ShadowRemovalNet: Efficient Real-Time Shadow Removal Method for Outdoor Robotics and Edge Computing Applications
ShadowRemovalNet offers an efficient solution for real-time shadow removal in outdoor robotics and edge computing applications, addressing challenges associated with Generative Adversarial Networks (GANs) and achieving higher frame rates compared to existing methods.
Pan-Mamba: Effective Pan-Sharpening with State Space Model
State-of-the-art pan-sharpening technique, Pan-Mamba, leverages the Mamba model for efficient global feature extraction and cross-modal information fusion.
© 2024 by Linnk AI