文章主题:加拿大博主, 2021年, 优秀论文, 计算机视觉
在网络世界中,一位名叫Louis Bouchard的加拿大博主,近期发布了一篇关于2021年不容错过的重要学术论文清单,共计40篇。这些论文的主题主要集中在计算机视觉领域。为了让大家更好地了解这些优秀的作品,我们特别挑选了部分论文进行展示。接下来,让我们一起领略这些论文的魅力吧!
1、DALL·E: Zero-Shot Text-to-Image Generation from OpenAI
论文链接:Zero-Shot Text-to-Image Generation – AMiner
代码地址:https://github.com/openai/DALL-E
视频解读:https://youtu.be/DJToDLBPovg
2、VOGUE: Try-On by StyleGAN Interpolation Optimization
论文链接:VOGUE: Try-On by StyleGAN Interpolation Optimization – AMiner
视频解读:https://youtu.be/i4MnLJGZbaM
3、Taming Transformers for High-Resolution Image Synthesis
论文链接:VOGUE: Try-On by StyleGAN Interpolation Optimization – AMiner
代码地址:https://github.com/CompVis/taming-transformers
视频解读:https://youtu.be/JfUTd8fjtX8
4、Thinking Fast And Slow in AI
论文链接:Thinking Fast And Slow In Ai – AMiner
视频解读:https://youtu.be/3nvAaVSQxs4
5、Automatic detection and quantification of floating marine macro-litter in aerial images
代码地址:https://github.com/amonleong/MARLIT视频解读:https://youtu.be/2dTSsdW0WYI
6、ShaRF: Shape-conditioned Radiance Fields from a Single View
论文链接:ShaRF: Shape-conditioned Radiance Fields from a Single View – AMiner代码地址:http://www.krematas.com/sharf/index.html
视频解读:https://youtu.be/gHkkrNMlGNg
7、Generative Adversarial Transformers
论文链接:Generative Adversarial Transformers – AMiner代码地址:https://github.com/dorarad/gansformer视频解读:https://youtu.be/HO-_t0UArd4
8、We Asked Artificial Intelligence to Create Dating Profiles. Would You Swipe Right?
视频解读:https://youtu.be/IoRH5u13P-4
9、Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
论文链接:Swin Transformer: Hierarchical Vision Transformer using Shifted Windows – AMiner
代码地址:https://github.com/microsoft/Swin-Transformer
视频解读:https://youtu.be/QcCJJOLCeJQ
在本篇中,我们将探讨IMAGE GANS与不同差异化渲染技术在 inverse graphics 和可解释的3D神经渲染领域的应用。
论文链接:Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering – AMiner视频解读:https://youtu.be/dvjwRBZ3Hnw
11、Deep nets: What have they ever done for vision?
论文链接:Deep Nets: What have they ever done for Vision? – AMiner视频解读:https://youtu.be/GhPDNzAVNDk
在本篇中,我们将探讨一种名为”Infinite Nature”的技术,该技术能够从单张图像中不断生成自然场景的无限视图。这种技术的出现,无疑为我们提供了一种全新的方式来欣赏和理解自然界的美丽。通过对单张图像进行处理和分析,Infinite Nature能够捕捉到图像中的各种视觉信息,并将其转化为丰富的自然场景。无论是壮观的山水画,还是细腻的花草植物,Infinite Nature都能为我们呈现出令人惊叹的视觉效果。此外,由于其 perpetual view generation 特性,Infinite Nature所生成的自然场景还能够根据观察者的需求进行实时调整,从而提供个性化的视觉体验。总的来说,Infinite Nature是一种具有创新性和实用性的技术,它不仅让我们能够更加深入地欣赏自然之美,同时也为我们的生活和娱乐带来更多的可能性。
论文链接:Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image – AMiner代码地址:https://github.com/google-research/google-research/tree/master/infinite_nature视频解读:https://youtu.be/NIOt1HLV_Mo在线试用:https://colab.research.google.com/github/google-research/google-research/blob/master/infinite_nature/infinite_nature_demo.ipynb#scrollTo=sCuRX1liUEVM
13、A Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control
论文链接:A Portable, Self-Contained Neuroprosthetic Hand With Deep Learning-Based Finger Control – AMiner视频解读:https://youtu.be/wNBrCRzlbVw
14、Total Relighting: Learning to Relight Portraits for Background Replacement
论文链接:Total Relighting: Learning To Relight Portraits For Background Replacement – AMiner视频解读:https://youtu.be/rVP2tcF_yRI
15、LASR: Learning Articulated Shape Reconstruction from a Monocular Video
论文链接:LASR – Learning Articulated Shape Reconstruction From a Monocular Video. – AMiner视频解读:https://youtu.be/lac7wqjS-8E
16、Enhancing Photorealism Enhancement
论文链接:Enhancing Photorealism Enhancement – AMiner代码地址:https://github.com/isl-org/PhotorealismEnhancement视频解读:https://youtu.be/3rYosbwXm1w
17、DefakeHop: A Light-Weight High-Performance Deepfake Detector
论文链接:DefakeHop: A Light-Weight High-Performance Deepfake Detector – AMiner视频解读:https://youtu.be/YMir8sRWRos
18、High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
论文链接:High-Resolution Photorealistic Image Translation in Real-Time – A Laplacian Pyramid Translation Network. – AMiner代码地址:https://github.com/csjliang/LPTN视频解读:https://youtu.be/X7WzlAyUGPo
19、Barbershop: GAN-based Image Compositing using Segmentation Masks
论文链接:Barbershop: GAN-based Image Compositing using Segmentation Masks – AMiner代码地址:https://github.com/ZPdesu/Barbershop视频解读:https://youtu.be/HtqYMvBVJD8
20、TextStyleBrush: Transfer of text aesthetics from a single example
论文链接:TextStyleBrush: Transfer of Text Aesthetics from a Single Example – AMiner代码地址:https://github.com/facebookresearch/IMGUR5K-Handwriting-Dataset?fbclid=IwAR0pRAxhf8Vg-5H3fA0BEaRrMeD21HfoCJ-so8V0qmWK7Ub21dvy_jqgiVo视频解读:https://youtu.be/hhAri5fl-XI
21、Animating Pictures with Eulerian Motion Fields
论文链接:Animating Pictures With Eulerian Motion Fields. – AMiner代码地址:https://eulerian.cs.washington.edu/视频解读:https://youtu.be/KgTa2r7d0I0
22、CVPR 2021 Best Paper Award: GIRAFFE – Controllable Image Generation
论文链接:GIRAFFE – Representing Scenes As Compositional Generative Neural Feature Fields. – AMiner代码地址:https://github.com/autonomousvision/giraffe视频解读:https://youtu.be/JIJkURAkCxM
23、GitHub Copilot & Codex: Evaluating Large Language Models Trained on Code
论文链接:Evaluating Large Language Models Trained on Code – AMiner代码地址:https://copilot.github.com/视频解读:https://youtu.be/az3oVVkTFB8
24、Apple: Recognizing People in Photos Through Private On-Device Machine Learning
视频解读:https://youtu.be/LIV-M-gFRFA
25、Image Synthesis and Editing with Stochastic Differential Equations
论文链接:SDEdit: Image Synthesis and Editing with Stochastic Differential Equations – AMiner代码地址:https://github.com/ermongroup/SDEdit视频解读:https://youtu.be/xoEkSWJSm1khttps://colab.research.google.com/drive/1KkLS53PndXKQpPlS1iK-k1nRQYmlb4aO?usp=sharing
26、Sketch Your Own GAN
论文链接:Sketch Your Own GAN – AMiner代码地址:https://github.com/PeterWang512/GANSketching视频解读:https://youtu.be/vz_wEQkTLk0
27、Teslas Autopilot Explained
在今年8月份的特斯拉AI日活动中,特斯拉AI总监Andrej Karpathy及其他相关人员展示了特斯拉如何利用八个摄像头捕捉图像,从而构建了一套基于视觉的自动驾驶系统。
视频解读:https://youtu.be/DTHqgDqkIRw
28、Styleclip: Text-driven manipulation of StyleGAN imagery
论文链接:StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery – AMiner代码地址:https://github.com/orpatashnik/StyleCLIP视频解读:https://youtu.be/RAXrwPskNsohttps://colab.research.google.com/github/orpatashnik/StyleCLIP/blob/main/notebooks/StyleCLIP_global.ipynb
TimeLens: 基于事件的视频帧插值方法
论文链接:TimeLens: Event-based Video Frame Interpolation – AMiner代码地址:https://github.com/uzh-rpg/rpg_timelens视频解读:https://youtu.be/HWA0yVXYRlk
30、Diverse Generation from a Single Video Made Possible
论文链接:Diverse Generation from a Single Video Made Possible – AMiner代码地址:https://nivha.github.io/vgpnn/视频解读:https://youtu.be/Uy8yKPEi1dg
31、Skillful Precipitation Nowcasting using Deep Generative Models of Radar
论文链接:Skilful Precipitation Nowcasting Using Deep Generative Models Of Radar – AMiner代码地址:https://github.com/deepmind/deepmind-research/tree/master/nowcasting视频解读:https://youtu.be/dlSIq64psEY
32、The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks
论文链接:The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks – AMiner代码地址:https://cocktail-fork.github.io/视频解读:https://youtu.be/Rpxufqt5r6I
33、ADOP: Approximate Differentiable One-Pixel Point Rendering
论文链接:ADOP: Approximate Differentiable One-Pixel Point Rendering – AMiner代码地址:https://github.com/darglein/ADOP视频解读:https://youtu.be/Jfph7Vld_Nw
34、(Style)CLIPDraw: Coupling Content and Style in Text-to-Drawing Synthesis
CLIPDraw论文链接:CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders – AMiner在线试用:https://colab.research.google.com/github/kvfrans/clipdraw/blob/main/clipdraw.ipynb
论文链接:StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Synthesis – AMiner在线试用:https://colab.research.google.com/github/pschaldenbrand/StyleCLIPDraw/blob/master/Style_ClipDraw.ipynb视频解读:https://youtu.be/5xzcIzHm8Wo
35、SwinIR: Image restoration using swin transformer
论文链接:SwinIR – Image Restoration Using Swin Transformer. – AMiner代码地址:https://github.com/JingyunLiang/SwinIR视频解读:https://youtu.be/GFm3RfrtDoUhttps://replicate.ai/jingyunliang/swinir
36、EditGAN: High-Precision Semantic Image Editing
论文链接:EditGAN: High-Precision Semantic Image Editing – AMiner代码地址:https://nv-tlabs.github.io/editGAN/视频解读:https://youtu.be/bus4OGyMQec
37、CityNeRF: Building NeRF at City Scale
论文链接:CityNeRF: Building NeRF at City Scale – AMiner代码地址:https://city-super.github.io/citynerf/视频解读:https://youtu.be/swfx0bJMIlY
38、ClipCap: CLIP Prefix for Image Captioning
论文链接:ClipCap: CLIP Prefix for Image Captioning – AMiner代码地址:https://github.com/rmokady/CLIP_prefix_caption视频解读:https://youtu.be/VQDrmuccWDo在线试用:https://colab.research.google.com/drive/1tuoAC5F4sC7qid56Z0ap-stR3rwdk0ZV?usp=sharing
The development of highly accurate protein structure prediction using Alphafold has revolutionized the field of structural biology.
当然,博主在整理的过程中也不能保证完美。经网友提醒,这里可以手动添加一项突破性研究:「AlphaFold」。
去年,谷歌旗下人工智能技术公司 DeepMind 宣布深度学习算法「Alphafold」破解了出现五十年之久的蛋白质分子折叠问题。2021年7月,AlphaFold 的论文正式发表在《Nature》杂志上。
这项研究被评为Nature年度技术突破,Alphafold 的缔造者之一 John Jumper 也被评为《Nature》2021 年度十大科学人物。DeepMind也已经将他们的预测结果免费开放给公众。
论文链接:https://www.nature.com/articles/s41586-021-03819-2对于你来说,2021年最令人印象深刻的论文又是哪篇呢?
【关于转载】本文转载于公众号“机器之心”,仅用于学术分享,有任何问题请与我们联系:report@aminer.cn
AI时代,拥有个人微信机器人AI助手!AI时代不落人后!
免费ChatGPT问答,办公、写作、生活好得力助手!
搜索微信号aigc666aigc999或上边扫码,即可拥有个人AI助手!