AIM21
* *Advances in Image Manipulation
* Contrastive Feature Loss for Image Prediction
* DeepFake MNIST+: A DeepFake Facial Animation Dataset
* Distilling Reflection Dynamics for Single-Image Reflection Removal
* Efficient Wavelet Boost Learning-Based Multi-stage Progressive Refinement Network for Underwater Image Enhancement
* Generalized Real-World Super-Resolution through Adversarial Robustness
* Graph2Pix: A Graph-Based Image to Image Translation Framework
* High Perceptual Quality Image Denoising with a Posterior Sampling CGAN
* Improving Key Human Features for Pose Transfer
* Manipulating Image Style Transformation via Latent-Space SVM
* Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
* Reducing Noise Pixels and Metric Bias in Semantic Inpainting on Segmentation Map
* Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement
* Saliency-Guided Transformer Network combined with Local Embedding for No-Reference Image Quality Assessment
* SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring
* Simple and Efficient Unpaired Real-world Super-Resolution using Image Statistics
* SMILE: Semantically-guided Multi-attribute Image and Layout Editing
* Sparse to Dense Motion Transfer for Face Image Animation
* Stochastic Image Denoising by Sampling from the Posterior Distribution
* SwinIR: Image Restoration Using Swin Transformer
* System for Fusing Color and Near-Infrared Images in Radiance Domain, A
* Test-Time Adaptation for Super-Resolution: You Only Need to Overfit on a Few More Images
* Underwater Image Color Correction Using Ensemble Colorization Network
* Unsupervised Generative Adversarial Networks with Cross-model Weight Transfer Mechanism for Image-to-image Translation
24 for AIM21