Awesome-VQGAN

Collecting papers and code resources relating VQGAN in various Computer Vision tasks.

Please star ⭐ this if you found this repo useful 😄. And please stay tuned for newer updates :).

Table of Contents

• Basics
• Super Resolution
• Image Inpainting
• Image Translation
• Multi-Modal Generation
• Point Cloud

Background 📖

Basics

Year	Title	Acronym	Publisher	Project	Code
2022	MaskGIT: Masked Generative Image Transformer	MaskGIT	CVPR	null	null
2021	Neural Discrete Representation Learning	VQ-VAE	NIPS	null	null
2021	Taming Transformers for High-Resolution Image Synthesis	VQGAN	CVPR	Project	Code

(back to top)

Super Resolution

Year	Title	Acronym	Publisher	Project	Code
2022	Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors	null	ACMMM	null	Code
2022	VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder	VQFR	ECCV	Project	Code
2022	Towards Robust Blind Face Restoration with Codebook Lookup Transformer	CodeFormer	NIPS	Project	Code

(back to top)

Image Inpainting

Year	Title	Acronym	Publisher	Project	Code
2022	High-Quality Pluralistic Image Completion via Code Shared VQGAN	null	Arxiv	null	null

(back to top)

Image Translation

Year	Title	Acronym	Publisher	Project	Code
2022	Vector Quantized Image-to-Image Translation	VQ-I2I	ECCV	Project	Code

(back to top)

Multi-Modal Generation

Year	Title	Acronym	Publisher	Project	Code
2022	VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance	VQGAN-CLIP	ECCV	null	Code
2022	Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning	VQGAN-CLIP	CVPR	null	Code
2021	M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers	M6-UFC	NIPS	null	Code

(back to top)

Point Cloud

Year	Title	Acronym	Publisher	Project	Code
2022	ShapeFormer: Transformer-based Shape Completion via Sparse Representation	ShapeFormer	NIPS	Project	Code

(back to top)