重磅推荐：2020年人工智能最精彩的25篇论文（附下载）
本文推薦整理的2020年人工智能最新突破的25篇論文，包含論文下載、視頻說明、代碼下載。
這是今年最精彩的人工智能方向的研究論文，本文幫您整理了。簡而言之，這是一份精心策劃人工智能和數據科學領域最新突破的論文清單，包含了視頻說明、論文下載、代碼下載等等，此外，每一篇論文的完整參考文獻都在文末進行羅列。
維護者：[louisfb01]:(https://github.com/louisfb01)
電子郵件 bouchard.lf@gmail.com
完整論文清單
[YOLOv4: Optimal Speed and Accuracy of Object Detection [1]]
[DeepFaceDrawing: Deep Generation of Face Images from Sketches?[2]]
[PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models?[3]]
[Unsupervised Translation of Programming Languages [4]]
[PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization [5]]
[High-Resolution Neural Face Swapping for Visual Effects?[6]]
[Swapping Autoencoder for Deep Image Manipulation [7]]
[GPT-3: Language Models are Few-Shot Learners?[8]]
[Learning Joint Spatial-Temporal Transformations for Video Inpainting [9]]
[Image GPT?-?Generative Pretraining from Pixels?[10]]
[Learning to Cartoonize Using White-box Cartoon Representations [11]]
[FreezeG: Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs?[12]]
[Neural Re-Rendering of Humans from a Single Image?[13]]
[I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image?[14]]:(#14)
[Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments [15]]
[RAFT: Recurrent All-Pairs Field Transforms for Optical Flow?[16]]
[Crowdsampling the Plenoptic Function?[17]]
[Old Photo Restoration via Deep Latent Space Translation [18]]
[Neural circuit policies enabling auditable autonomy?[19]]
[Lifespan Age Transformation Synthesis [20]]
[COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning?[21]]
[Stylized Neural Painting?[22]]
[Is a Green Screen Really Necessary for Real-Time Portrait Matting??[23]]
[ADA: Training Generative Adversarial Networks with Limited Data?[24]]
[Improving Data‐Driven Global Weather Prediction Using Deep Convolutional Neural Networks on a Cubed Sphere [25]]
[Paper references]
YOLOv4: Optimal Speed and Accuracy of Object Detection [1]
This 4th version has been recently introduced in April 2020 by Alexey Bochkovsky et al. in the paper "YOLOv4: Optimal Speed and Accuracy of Object Detection". The main goal of this algorithm was to make a super-fast object detector with high quality in terms of accuracy.
[The YOLOv4 algorithm | Introduction to You Only Look Once, Version 4 | Real Time Object Detection ]:(https://youtu.be/CtjZFkO5RPw) - 短視頻說明
[The YOLOv4 algorithm | Introduction to You Only Look Once, Version 4 | Real-Time Object Detection]:(https://medium.com/what-is-artificial-intelligence/the-yolov4-algorithm-introduction-to-you-only-look-once-version-4-real-time-object-detection-5fd8a608b0fa) - 簡短閱讀
[YOLOv4: Optimal Speed and Accuracy of Object Detection]:(https://arxiv.org/abs/2004.10934) - 論文下載
[Click here for the Yolo v4 code]:(https://github.com/AlexeyAB/darknet) - 代碼下載
DeepFaceDrawing: Deep Generation of Face Images from Sketches?[2]
You can now generate high-quality face images from rough or even incomplete sketches with zero drawing skills using this new image-to-image translation technique! If your drawing skills as bad as mine you can even adjust how much the eyes, mouth, and nose will affect the final image! Let's see if it really works and how they did it.
[AI Generates Real Faces From Sketches! DeepFaceDrawing Overview | Image-to-image translation in 2020]:(https://youtu.be/djXdgCVB0oM) - 短視頻說明
[AI Generates Real Faces From Sketches!]:(https://medium.com/what-is-artificial-intelligence/ai-generates-real-faces-from-sketches-8ccbac5d2b2e) - 簡短閱讀
[DeepFaceDrawing: Deep Generation of Face Images from?Sketches]:(http://geometrylearning.com/paper/DeepFaceDrawing.pdf) - 論文下載
[Click here for the DeepFaceDrawing code]:(https://github.com/IGLICT/DeepFaceDrawing-Jittor) - 代碼下載
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models?[3]
This new algorithm transforms a blurry image into a high-resolution image! It can take a super low-resolution 16x16 image and turn it into a 1080p high definition human face! You don't believe me? Then you can do just like me and try it on yourself in less than a minute! But first, let's see how they did that.
[This AI makes blurry faces look 60 times sharper! Introduction to PULSE: photo upsampling]:(https://youtu.be/cgakyOI9r8M) - 短視頻說明
[This AI makes blurry faces look 60 times sharper]:(https://medium.com/what-is-artificial-intelligence/this-ai-makes-blurry-faces-look-60-times-sharper-7fcd3b820910) - 簡短閱讀
[PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models]:(https://arxiv.org/abs/2003.03808) - 論文下載
[Click here for the PULSE code]:(https://github.com/adamian98/pulse) - 代碼下載
Unsupervised Translation of Programming Languages [4]
This new model converts code from a programming language to another without any supervision! It can take a Python function and translate it into a C++ function, and vice-versa, without any prior examples! It understands the syntax of each language and can thus generalize to any programming language! Let's see how they did that.
[This AI translates code from a programming language to another | Facebook TransCoder Explained]:(https://youtu.be/u6kM2lkrGQk) - 短視頻說明
[This AI translates code from a programming language to another | Facebook TransCoder Explained]:(https://medium.com/what-is-artificial-intelligence/this-ai-translates-code-from-a-programming-language-to-another-facebook-transcoder-explained-3017d052f4fd) - 簡短閱讀
[Unsupervised Translation of Programming Languages]:(https://arxiv.org/abs/2006.03511) - 論文下載
[Click here for the Transcoder code]:(https://github.com/facebookresearch/TransCoder?utm_source=catalyzex.com) - 代碼下載
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization [5]
This AI Generates 3D high-resolution reconstructions of people from 2D images! It only needs a single image of you to generate a 3D avatar that looks just like you, even from the back!
[AI Generates 3D high-resolution reconstructions of people from 2D images | Introduction to PIFuHD]:(https://youtu.be/ajWtdm05-6g) - 短視頻說明
[AI Generates 3D high-resolution reconstructions of people from 2D images | Introduction to PIFuHD]:(https://medium.com/towards-artificial-intelligence/ai-generates-3d-high-resolution-reconstructions-of-people-from-2d-images-introduction-to-pifuhd-d4aa515a482a) - 簡短閱讀
[PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization]:(https://arxiv.org/pdf/2004.00452.pdf) - 論文下載
[Click here for the PiFuHD code]:(https://github.com/facebookresearch/pifuhd) - 代碼下載
High-Resolution Neural Face Swapping for Visual Effects?[6]
Researchers at Disney developed a new High-Resolution Face Swapping algorithm for Visual Effects in 論文下載 of the same name. It is capable of rendering photo-realistic results at megapixel resolution. Working for Disney, they are most certainly the best team for this work. Their goal is to swap the face of a target actor from a source actor while maintaining the actor's performance. This is incredibly challenging and is useful in many circumstances, such as changing the age of a character, when an actor is not available, or even when it involves a stunt scene that would be too dangerous for the main actor to perform. The current approaches require a lot of frame-by-frame animation and post-processing by professionals.
[Disney's New High Resolution Face Swapping Algorithm | New 2020 Face Swap Technology Explained]:(https://youtu.be/EzyhA46DQWA) - 短視頻說明
[Disney's New High-Resolution Face Swapping Algorithm | New 2020 Face Swap Technology Explained]:(https://medium.com/what-is-artificial-intelligence/disneys-new-high-resolution-face-swapping-algorithm-new-2020-face-swap-technology-explained-da7dc8caa2f2) - 簡短閱讀
[High-Resolution Neural Face Swapping for Visual Effects]:(https://studios.disneyresearch.com/2020/06/29/high-resolution-neural-face-swapping-for-visual-effects/) - 論文下載
Swapping Autoencoder for Deep Image Manipulation [7]
This new technique can change the texture of any picture while staying realistic using complete unsupervised training! The results look even better than what GANs can achieve while being way faster! It could even be used to create deepfakes!
[Texture-Swapping AI beats GANs for Image Manipulation! New Technique: Swapping Autoencoder Explained]:(https://youtu.be/hPR4cRzQY0s) - 短視頻說明
[Texture-Swapping AI beats GANs for Image Manipulation!]:(https://medium.com/what-is-artificial-intelligence/texture-swapping-ai-beats-gans-for-image-manipulation-e05700782183) - 簡短閱讀
[Swapping Autoencoder for Deep Image Manipulation]:(https://arxiv.org/abs/2007.00653) - 論文下載
[Click here for the Swapping autoencoder code]:(https://github.com/rosinality/swapping-autoencoder-pytorch?utm_source=catalyzex.com) - 代碼下載
GPT-3: Language Models are Few-Shot Learners?[8]
The current state-of-the-art NLP systems struggle to generalize to work on different tasks. They need to be fine-tuned on datasets of thousands of examples while humans only need to see a few examples to perform a new language task. This was the goal behind GPT-3, to improve the task-agnostic characteristic of language models.
[OpenAI's New Language Generator: GPT-3 | This AI Generates Code, Websites, Songs & More From Words]:(https://youtu.be/gDDnTZchKec) - 短視頻說明
[Can GPT-3 Really Help You and Your Company?]:(https://medium.com/towards-artificial-intelligence/can-gpt-3-really-help-you-and-your-company-84dac3c5b58a) - 簡短閱讀
[Language Models are Few-Shot Learners]:(https://arxiv.org/pdf/2005.14165.pdf) - 論文下載
[Click here for GPT-3's GitHub page]:(https://github.com/openai/gpt-3) - The GitHub
Learning Joint Spatial-Temporal Transformations for Video Inpainting [9]
This AI can fill the missing pixels behind a removed moving object and reconstruct the whole video with way more accuracy and less blurriness than current state-of-the-art approaches!
[This AI Takes a Video and Fills the Missing Pixels Behind an Object ! Video Inpainting]:(https://youtu.be/MAxMYGoN5U0) - 短視頻說明
[This AI takes a video and fills the missing pixels behind an object!]:(https://medium.com/towards-artificial-intelligence/this-ai-takes-a-video-and-fills-the-missing-pixels-behind-an-object-video-inpainting-9be38e141f46) - 簡短閱讀
[Learning Joint Spatial-Temporal Transformations for Video Inpainting]:(https://arxiv.org/abs/2007.10247) - 論文下載
[Click here for this Video Inpainting code]:(https://github.com/researchmm/STTN?utm_source=catalyzex.com) - 代碼下載
Image GPT?-?Generative Pretraining from Pixels?[10]
A good AI, like the one used in Gmail, can generate coherent text and finish your phrase. This one uses the same principles in order to complete an image! All done in an unsupervised training with no labels required at all!
[This AI Can Generate the Other Half of a Picture Using a GPT Model]:(https://youtu.be/FwXQ568_io0) - 短視頻說明
[This AI Can Generate the Other Half of a Picture Using a GPT Model]:(https://medium.com/towards-artificial-intelligence/this-ai-can-generate-the-pixels-of-half-of-a-picture-from-nothing-using-a-nlp-model-7d7ba14b5522) - 簡短閱讀
[Image GPT?-?Generative Pretraining from Pixels]:(https://openai.com/blog/image-gpt/) - 論文下載
[Click here for the OpenAI's Image GPT code]:(https://github.com/openai/image-gpt) - 代碼下載
Learning to Cartoonize Using White-box Cartoon Representations [11]
This AI can cartoonize any picture or video you feed it in the cartoon style you want! Let's see how it does that and some amazing examples. You can even try it yourself on the website they created as I did for myself!
[This AI can cartoonize any picture or video you feed it! Paper Introduction & Results examples]:(https://youtu.be/GZVsONq3qtg) - 短視頻說明
[This AI can cartoonize any picture or video you feed it! Paper Introduction & Results examples]:(https://medium.com/what-is-artificial-intelligence/this-ai-can-cartoonize-any-picture-or-video-you-feed-it-paper-introduction-results-examples-d7e400d8c3e8) - 簡短閱讀
[Learning to Cartoonize Using White-box Cartoon Representations]:(https://systemerrorwang.github.io/White-box-Cartoonization/paper/06791.pdf) - 論文下載
[Click here for the Cartoonize code]:(https://github.com/SystemErrorWang/White-box-Cartoonization) - 代碼下載
FreezeG: Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs?[12]
This face generating model is able to transfer normal face photographs into distinctive styles such as Lee Mal-Nyeon's cartoon style, the Simpsons, arts, and even dogs! The best thing about this new technique is that it's super simple and significantly outperforms previous techniques used in GANs.
[This Face Generating Model Transfers Real Face Photographs Into Distinctive Cartoon Styles | FreezeG]:(https://youtu.be/RvPUVniQiuw) - 短視頻說明
[This Face Generating Model Transfers Real Face Photographs Into Distinctive Cartoon Styles]:(https://medium.com/what-is-artificial-intelligence/this-face-generating-model-transfers-real-face-photographs-into-distinctive-cartoon-styles-33dde907737a) - 簡短閱讀
[Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs]:(https://arxiv.org/pdf/2002.10964.pdf) - 論文下載
[Click here for the FreezeG code]:(https://github.com/sangwoomo/freezeD?utm_source=catalyzex.com) - 代碼下載
Neural Re-Rendering of Humans from a Single Image?[13]
The algorithm represents body pose and shape as a parametric mesh which can be reconstructed from a single image and easily reposed. Given an image of a person, they are able to create synthetic images of the person in different poses or with different clothing obtained from another input image.
[Transfer clothes between photos using AI. From a single image!]:(https://youtu.be/E7fGsSNKMc4) - 短視頻說明
[Transfer clothes between photos using AI. From a single image!]:(https://medium.com/dataseries/transfer-clothes-between-photos-using-ai-from-a-single-image-4430a291afd7) - 簡短閱讀
[Neural Re-Rendering of Humans from a Single Image]:(http://gvv.mpi-inf.mpg.de/projects/NHRR/data/1415.pdf) - 論文下載
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image?[14]
DescHere
[Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image! With Code Publicly Avaibable!]:(https://youtu.be/tDz2wTixcrI) - 短視頻說明
[Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image! With Code Publicly Avaibable!]:(https://medium.com/dataseries/accurate-3d-human-pose-and-mesh-estimation-from-a-single-rgb-image-with-code-publicly-avaibable-b7cc995bcf2a) - 簡短閱讀
[I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image]:(https://www.catalyzex.com/paper/arxiv:2008.03713?fbclid=IwAR1pQGBhIwO4gW4mVZm1UEtyPLyZInsLZMyq3EoANaWxGO0CZ00Sj3ViM7I) - 論文下載
Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments [15]
Language-guided navigation is a widely studied field and a very complex one. Indeed, it may seem simple for a human to just walk through a house to get to your coffee that you left on your nightstand to the left of your bed. But it is a whole other story for an agent, which is an autonomous AI-driven system using deep learning to perform tasks.
[Language-Guided Navigation in 3D Environment | Facebook AI Research (with code publicly available!)]:(https://youtu.be/Fw_RUlUjuN4) - 短視頻說明
[Language-Guided Navigation in a 3D Environment]:(https://medium.com/r/?url=https%3A%2F%2Fbecominghuman.ai%2Flanguage-guided-navigation-in-a-3d-environment-e3cf4102fb89) - 簡短閱讀
[Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments]:(https://arxiv.org/pdf/2004.02857.pdf) - 論文下載
[Click here for the VLN-CE code]:(https://github.com/jacobkrantz/VLN-CE) - 代碼下載
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow?[16]
ECCV 2020 Best Paper Award Goes to Princeton Team. They developed a new end-to-end trainable model for optical flow. Their method beats state-of-the-art architectures' accuracy across multiple datasets and is way more efficient. They even made 代碼下載 available for everyone on their Github!
[ECCV 2020 Best Paper Award | RAFT: A New Deep Network Architecture For Optical Flow | WITH CODE]:(https://youtu.be/OSEuYBwOSGI) - 短視頻說明
[ECCV 2020 Best Paper Award | A New Architecture For Optical Flow]:(https://medium.com/towards-artificial-intelligence/eccv-2020-best-paper-award-a-new-architecture-for-optical-flow-3298c8a40dc7) - 簡短閱讀
[RAFT: Recurrent All-Pairs Field Transforms for Optical Flow]:(https://arxiv.org/pdf/2003.12039.pdf) - 論文下載
[Click here for the RAFT code]:(https://github.com/princeton-vl/RAFT) - 代碼下載
Crowdsampling the Plenoptic Function?[17]
Using tourists' public photos from the internet, they were able to reconstruct multiple viewpoints of a scene conserving the realistic shadows and lighting! This is a huge advancement of the state-of-the-art techniques for photorealistic scene rendering and their results are simply amazing.
[Reconstruct photorealistic scenes from tourists public photos on the internet!]:(https://youtu.be/F_JqJNBvJ64) - 短視頻說明
[Reconstruct Photorealistic Scenes from Tourists' Public Photos on the Internet!]:(https://medium.com/towards-artificial-intelligence/reconstruct-photorealistic-scenes-from-tourists-public-photos-on-the-internet-bb9ad39c96f3) - 簡短閱讀
[Crowdsampling the Plenoptic Function]:(https://research.cs.cornell.edu/crowdplenoptic/) - 論文下載
[Click here for the Crowdsampling code]:(https://github.com/zhengqili/Crowdsampling-the-Plenoptic-Function) - 代碼下載
Old Photo Restoration via Deep Latent Space Translation [18]
Imagine having the old, folded, and even torn pictures of your grandmother when she was 18 years old in high definition with zero artifacts. This is called old photo restoration and this paper just opened a whole new avenue to address this problem using a deep learning approach.
[Old Photo Restoration Using Deep Learning | 2020 Novel Approach Explained & Results]:(https://youtu.be/QUmrIpl0afQ) - 短視頻說明
[Old Photo Restoration using Deep Learning]:(https://medium.com/towards-artificial-intelligence/old-photo-restoration-using-deep-learning-47d4ab1bdc4d) - 簡短閱讀
[Old Photo Restoration via Deep Latent Space Translation]:(https://arxiv.org/pdf/2009.07047.pdf) - 論文下載
[Click here for the Old Photo Restoration code]:(https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life?utm_source=catalyzex.com) - 代碼下載
Neural circuit policies enabling auditable autonomy?[19]
Researchers from IST Austria and MIT have successfully trained a self-driving car using a new artificial intelligence system based on the brains of tiny animals, such as threadworms. They achieved that with only a few neurons able to control the self-driving car, compared to the millions of neurons needed by the popular deep neural networks such as Inceptions, Resnets, or VGG. Their network was able to completely control a car using only 75 000 parameters, composed of 19 control neurons, rather than millions!
[A new brain-inspired intelligent system can drive a car using only 19 control neurons!]:(https://youtu.be/wAa358pNDkQ) - 短視頻說明
[A New Brain-inspired Intelligent System Drives a Car Using Only 19 Control Neurons!]:(https://medium.com/towards-artificial-intelligence/a-new-brain-inspired-intelligent-system-drives-a-car-using-only-19-control-neurons-1ed127107db9) - 簡短閱讀
[Neural circuit policies enabling auditable autonomy]:(https://www.nature.com/articles/s42256-020-00237-3.epdf?sharing_token=xHsXBg2SoR9l8XdbXeGSqtRgN0jAjWel9jnR3ZoTv0PbS_e49wmlSXvnXIRQ7wyir5MOFK7XBfQ8sxCtVjc7zD1lWeQB5kHoRr4BAmDEU0_1-UN5qHD5nXYVQyq5BrRV_tFa3_FZjs4LBHt-yebsG4eQcOnNsG4BenK3CmBRFLk%3D) - 論文下載
[Click here for the NCP code]:(https://github.com/mlech26l/keras-ncp) - 代碼下載
Lifespan Age Transformation Synthesis [20]
A team of researchers from Adobe Research developed a new technique for age transformation synthesis based on only one picture from the person. It can generate the lifespan pictures from any picture you sent it.
[Lifespan Age Transformation Synthesis | Generate Younger & Older Versions of Yourself !]:(https://youtu.be/xA-3cWJ4Y9Q) - 短視頻說明
[Generate Younger & Older Versions of Yourself!]:(https://medium.com/towards-artificial-intelligence/generate-younger-older-versions-of-yourself-1a87f970f3da) - 簡短閱讀
[Lifespan Age Transformation Synthesis]:(https://arxiv.org/pdf/2003.09764.pdf) - 論文下載
[Click here for the Lifespan age transformation synthesis code]:(https://github.com/royorel/Lifespan_Age_Transformation_Synthesis) - 代碼下載
DeOldify
DeOldify is a technique to colorize and restore old black and white images or even film footage. It was developed and is still getting updated by only one person Jason Antic. It is now the state of the art way to colorize black and white images, and everything is open-sourced, but we will get back to this in a bit.
[This AI can Colorize your Black & White Photos with Full Photorealistic Renders! (DeOldify)]:(https://youtu.be/1EP_Lq04h4M) - 短視頻說明
[This AI can Colorize your Black & White Photos with Full Photorealistic Renders! (DeOldify)]:(https://medium.com/towards-artificial-intelligence/this-ai-can-colorize-your-black-white-photos-with-full-photorealistic-renders-deoldify-bf1eed5cb02a) - 簡短閱讀
[Click here for the DeOldify code]:(https://github.com/jantic/DeOldify) - 代碼下載
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning?[21]
As the name states, it uses transformers to generate accurate text descriptions for each sequence of a video, using both the video and a general description of it as inputs.
[Video to Text Description Using Deep Learning and Transformers | COOT]:(https://youtu.be/5TRp5SuEtoY) - 短視頻說明
[Video to Text Description Using Deep Learning and Transformers | COOT]:(https://medium.com/towards-artificial-intelligence/video-to-text-description-using-deep-learning-and-transformers-coot-e05b8d0db110) - 簡短閱讀
[COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning]:(https://arxiv.org/pdf/2011.00597.pdf) - 論文下載
[Click here for the COOT code]:(https://github.com/gingsi/coot-videotext) - 代碼下載
Stylized Neural Painting?[22]
This Image-to-Painting Translation method simulates a real painter on multiple styles using a novel approach that does not involve any GAN architecture, unlike all the current state-of-the-art approaches!
[Image-to-Painting Translation With Style Transfer]:(https://youtu.be/dzJStceOaQs) - 短視頻說明
[Image-to-Painting Translation With Style Transfer]:(https://medium.com/towards-artificial-intelligence/image-to-painting-translation-with-style-transfer-508618596409) - 簡短閱讀
[Stylized Neural Painting]:(https://arxiv.org/abs/2011.08114) - 論文下載
[Click here for the Stylized Neural Painting code]:(https://github.com/jiupinjia/stylized-neural-painting) - 代碼下載
Is a Green Screen Really Necessary for Real-Time Portrait Matting??[23]
Human matting is an extremely interesting task where the goal is to find any human in a picture and remove the background from it. It is really hard to achieve due to the complexity of the task, having to find the person or people with the perfect contour. In this post, I review the best techniques used over the years and a novel approach published on November 29th, 2020. Many techniques are using basic computer vision algorithms to achieve this task, such as the GrabCut algorithm, which is extremely fast, but not very precise.
[High-Quality Background Removal Without Green Screens | State of the Art Approach Explained]:(https://youtu.be/rUo0wuVyefU) - 短視頻說明
[High-Quality Background Removal Without Green Screens]:(https://medium.com/datadriveninvestor/high-quality-background-removal-without-green-screens-8e61c69de63) - 簡短閱讀
[Is a Green Screen Really Necessary for Real-Time Portrait Matting?]:(https://arxiv.org/pdf/2011.11961.pdf) - 論文下載
[Click here for the MODNet code]:(https://github.com/ZHKKKe/MODNet) - 代碼下載
ADA: Training Generative Adversarial Networks with Limited Data?[24]
With this new training method developed by NVIDIA, you can train a powerful generative model with one-tenth of the images! Making possible many applications that do not have access to so many images!
[GAN Training Breakthrough for Limited Data Applications & New NVIDIA Program! NVIDIA Research]:(https://youtu.be/9fVNtVr_luc) - 短視頻說明
[GAN Training Breakthrough for Limited Data Applications & New NVIDIA Program! NVIDIA Research]:(https://medium.com/towards-artificial-intelligence/gan-training-breakthrough-for-limited-data-applications-new-nvidia-program-nvidia-research-3652c4c172e6) - 簡短閱讀
[Training Generative Adversarial Networks with Limited Data]:(https://arxiv.org/abs/2006.06676) - 論文下載
[Click here for the ADA code]:(https://github.com/NVlabs/stylegan2-ada) - 代碼下載
Improving Data‐Driven Global Weather Prediction Using Deep Convolutional Neural Networks on a Cubed Sphere?[25]
With this new training method developed by NVIDIA, you can train a powerful generative model with one-tenth of the images! Making possible many applications that do not have access to so many images!
[An AI Predicting Faster and More Accurate Weather Forecasts]:(https://youtu.be/C7dNU298A0A) - 短視頻說明
[AI is Predicting Faster and More Accurate Weather Forecasts]:(https://medium.com/towards-artificial-intelligence/ai-is-predicting-faster-and-more-accurate-weather-forecasts-5d99a1d9c4f) - 簡短閱讀
[Improving Data‐Driven Global Weather Prediction Using Deep Convolutional Neural Networks on a Cubed Sphere]:(https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2020MS002109) - 論文下載
[Click here for the weather forecasting code]:(https://github.com/jweyn/DLWP-CS) - 代碼下載
論文參考
[1] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, Yolov4: Optimal speed and accuracy of object detection, 2020. arXiv:2004.10934 [cs.CV].
[2] S.-Y. Chen, W. Su, L. Gao, S. Xia, and H. Fu, "DeepFaceDrawing: Deep generation of face images from sketches," ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH2020), vol. 39, no. 4, 72:1–72:16, 2020.
[3] S. Menon, A. Damian, S. Hu, N. Ravi, and C. Rudin, Pulse: Self-supervised photo upsampling via latent space exploration of generative models, 2020. arXiv:2003.03808 [cs.CV].
[4] M.-A. Lachaux, B. Roziere, L. Chanussot, and G. Lample, Unsupervised translation of programming languages, 2020. arXiv:2006.03511 [cs.CL].
[5] S. Saito, T. Simon, J. Saragih, and H. Joo, Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization, 2020. arXiv:2004.00452 [cs.CV].
[6] J. Naruniec, L. Helminger, C. Schroers, and R. Weber, "High-resolution neural face-swapping for visual effects," Computer Graphics Forum, vol. 39, pp. 173–184, Jul. 2020.doi:10.1111/cgf.14062.
[7] T. Park, J.-Y. Zhu, O. Wang, J. Lu, E. Shechtman, A. A. Efros, and R. Zhang,Swappingautoencoder for deep image manipulation, 2020. arXiv:2007.00653 [cs.CV].
[8] T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P.Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S.Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amodei,"Language models are few-shot learners," 2020. arXiv:2005.14165 [cs.CL].
[9] Y. Zeng, J. Fu, and H. Chao, Learning joint spatial-temporal transformations for video in-painting, 2020. arXiv:2007.10247 [cs.CV].
[10] M. Chen, A. Radford, R. Child, J. Wu, H. Jun, D. Luan, and I. Sutskever, "Generative pretraining from pixels," in Proceedings of the 37th International Conference on Machine Learning, H. D. III and A. Singh, Eds., ser. Proceedings of Machine Learning Research, vol. 119, Virtual: PMLR, 13–18 Jul 2020, pp. 1691–1703. [Online]. Available:http://proceedings.mlr.press/v119/chen20s.html.
[11] Xinrui Wang and Jinze Yu, "Learning to Cartoonize Using White-box Cartoon Representations.", IEEE Conference on Computer Vision and Pattern Recognition, June 2020.
[12] S. Mo, M. Cho, and J. Shin, Freeze the discriminator: A simple baseline for fine-tuning gans,2020. arXiv:2002.10964 [cs.CV].
[13] K. Sarkar, D. Mehta, W. Xu, V. Golyanik, and C. Theobalt, "Neural re-rendering of humans from a single image," in European Conference on Computer Vision (ECCV), 2020.
[14] G. Moon and K. M. Lee, "I2l-meshnet: Image-to-lixel prediction network for accurate 3d human pose and mesh estimation from a single rgb image," in European Conference on ComputerVision (ECCV), 2020
[15] J. Krantz, E. Wijmans, A. Majumdar, D. Batra, and S. Lee, "Beyond the nav-graph: Vision-and-language navigation in continuous environments," 2020. arXiv:2004.02857 [cs.CV].
[16] Z. Teed and J. Deng, Raft: Recurrent all-pairs field transforms for optical flow, 2020. arXiv:2003.12039 [cs.CV].
[17] Z. Li, W. Xian, A. Davis, and N. Snavely, "Crowdsampling the plenoptic function," inProc.European Conference on Computer Vision (ECCV), 2020.
[18] Z. Wan, B. Zhang, D. Chen, P. Zhang, D. Chen, J. Liao, and F. Wen, Old photo restoration via deep latent space translation, 2020. arXiv:2009.07047 [cs.CV].
[19] Lechner, M., Hasani, R., Amini, A. et al. Neural circuit policies enabling auditable autonomy. Nat Mach Intell 2, 642–652 (2020). https://doi.org/10.1038/s42256-020-00237-3
[20] R. Or-El, S. Sengupta, O. Fried, E. Shechtman, and I. Kemelmacher-Shlizerman, "Lifespanage transformation synthesis," in Proceedings of the European Conference on Computer Vision(ECCV), 2020.
[21] S. Ging, M. Zolfaghari, H. Pirsiavash, and T. Brox, "Coot: Cooperative hierarchical trans-former for video-text representation learning," in Conference on Neural Information ProcessingSystems, 2020.
[22] Z. Zou, T. Shi, S. Qiu, Y. Yuan, and Z. Shi, Stylized neural painting, 2020. arXiv:2011.08114[cs.CV].
[23] Z. Ke, K. Li, Y. Zhou, Q. Wu, X. Mao, Q. Yan, and R. W. Lau, "Is a green screen really necessary for real-time portrait matting?" ArXiv, vol. abs/2011.11961, 2020.
[24] T. Karras, M. Aittala, J. Hellsten, S. Laine, J. Lehtinen, and T. Aila, Training generative adversarial networks with limited data, 2020. arXiv:2006.06676 [cs.CV].
[25] J. A. Weyn, D. R. Durran, and R. Caruana, “Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere”, Journal of Advances in Modeling Earth Systems, vol. 12, no. 9, Sep. 2020, issn: 1942–2466.doi:10.1029/2020ms002109
往期精彩回顧適合初學者入門人工智能的路線及資料下載機器學習及深度學習筆記等資料打印機器學習在線手冊深度學習筆記專輯《統計學習方法》的代碼復現專輯 AI基礎下載機器學習的數學基礎專輯 獲取本站知識星球優惠券，復制鏈接直接打開： https://t.zsxq.com/qFiUFMV 本站qq群704220115。加入微信群請掃碼：總結
以上是生活随笔為你收集整理的重磅推荐：2020年人工智能最精彩的25篇论文（附下载）的全部內容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： 企业微信如何设置发票抬头 管理员在企业微
- 下一篇： Win7系统更换软件图标的详细方法