awesome4me (Paper and Code)

Image to Image Translation

2023

• Improving Diffusion-based Image Translation using Asymmetric Gradient Guidance
• Zero-Shot Contrastive loss for Text guided diffusion image style transfer [code]

2022

• Splicing ViT Features of Semantic Apperance Transfer
• SHUNIT: Style Harmonization for Unpaired Image-to-Image Translation
• Unifying Diffusion Model’ Latent Space, With Aapplications to Cyclediffusion and guidance
• Diffusion-based Image Translation using Disentangled Style and Content Representation

Image Synthesis

2023

• Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
• Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate
• Cross-domain Compositing with Pretrained Diffusion Models

2022

• Blended Latent Diffusion
• Blended Diffusion for Text-driven Editing of Natural Images

2021

• AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

Robust Model (Augmentation, Domain shift, etc..)

2023

• Synthetic Data from Diffusion Models Improves ImageNet Classification

2022

• Test-Time Training with Masked Autoencoders

2019

• Benchmarking Robustness in Object Detection: Autonomous Driving when winter is coming

Augmentation with generative image

2023

• Effective Data Augmentation with Diffusion Models

2018

• GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks

Sign Language

2022

• MLSLT: Towards Multilingual Sign Language Translation

CLIP code

• CLIP (Official)
• CLIP Training (not official but easy reference code)
• Open CLIP (semi official)