2021年值得阅读的AI领域论文（偏重计算机视觉方向）

一位国外博主以时间顺序总结了40篇2021年的AI论文。需要的可以查看。
原文链接中有论文原文和代码
原文链接：https://www.louisbouchard.ai/2021-ai-papers-review/

文章列表
DALL·E: Zero-Shot Text-to-Image Generation from OpenAI [1]
VOGUE: Try-On by StyleGAN Interpolation Optimization [2]
Taming Transformers for High-Resolution Image Synthesis [3]
Thinking Fast And Slow in AI [4]
Automatic detection and quantification of floating marine macro-litter in aerial images [5]
ShaRF: Shape-conditioned Radiance Fields from a Single View [6]
Generative Adversarial Transformers [7]
We Asked Artificial Intelligence to Create Dating Profiles. Would You Swipe Right? [8]
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows [9]
IMAGE GANS MEET DIFFERENTIABLE RENDERING FOR INVERSE GRAPHICS AND INTERPRETABLE 3D NEURAL RENDERING [10]
Deep nets: What have they ever done for vision? [11]
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image [12]
Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control [13]
Total Relighting: Learning to Relight Portraits for Background Replacement [14]
LASR: Learning Articulated Shape Reconstruction from a Monocular Video [15]
Enhancing Photorealism Enhancement [16]
DefakeHop: A Light-Weight High-Performance Deepfake Detector [17]
High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network [18]
Barbershop: GAN-based Image Compositing using Segmentation Masks [19]
TextStyleBrush: Transfer of text aesthetics from a single example [20]
Animating Pictures with Eulerian Motion Fields [21]
CVPR 2021 Best Paper Award: GIRAFFE - Controllable Image Generation [22]
GitHub Copilot & Codex: Evaluating Large Language Models Trained on Code [23]
Apple: Recognizing People in Photos Through Private On-Device Machine Learning [24]
Image Synthesis and Editing with Stochastic Differential Equations [25]
Sketch Your Own GAN [26]
Tesla’s Autopilot Explained [27]
Styleclip: Text-driven manipulation of StyleGAN imagery [28]
TimeLens: Event-based Video Frame Interpolation [29]
Diverse Generation from a Single Video Made Possible [30]
Skillful Precipitation Nowcasting using Deep Generative Models of Radar [31]
The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks [32]
ADOP: Approximate Differentiable One-Pixel Point Rendering [33]
(Style)CLIPDraw: Coupling Content and Style in Text-to-Drawing Synthesis [34]
SwinIR: Image restoration using swin transformer [35]
EditGAN: High-Precision Semantic Image Editing [36]
CityNeRF: Building NeRF at City Scale [37]
ClipCap: CLIP Prefix for Image Captioning [38]
Paper references