Top 10 Computer Vision papers 2020

This post was originally published by Matt Mayo Editor at KD Nuggets

The top 10 computer vision papers in 2020 with video demos, articles, code, and paper reference.

Image for post

Even with everything that happened in the world this year, we still had the chance to see a lot of amazing research come out. Especially in the field of artificial intelligence and more precisely computer vision. More, many important aspects were highlighted this year, like the ethical aspects, important biases, and much more. Artificial intelligence and our understanding of the human brain and its link to AI is constantly evolving, showing promising applications in the soon future, which I will definitely cover.

Here are my top 10 of the most interesting research papers of the year in computer vision, in case you missed any of them. In short, it is basically a curated list of the latest breakthroughs in AI and CV with a clear video explanationlink to a more in-depth article, and code (if applicable). Enjoy the read, and let me know if I missed any important papers in the comments, or by contacting me directly on LinkedIn!

The complete reference to each paper is listed at the end of this article.

Access the complete list in a GitHub repository

Tag me on Twitter (@Whats_AI) or LinkedIn (Louis (What’s AI) Bouchard) if you share the article!

Have you ever wondered how the ocean would look like without water Remove this blue-green tint of the underwater pictures, and still have the true colors of a coral reef? Well, using computer vision and machine learning algorithms, researchers from the University of Haifa were able to accomplish exactly that!

Click here for the Sea-thru code

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!

Click here for the NCP code

This new method is able to generate a complete 3-dimensional scene and has the ability to decide the lighting of the scene. All this with very limited computation costs and amazing results compared to previous approaches.

Click here for the NeRV code (available soon)

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.

Click here for the Yolo v4 code

This new algorithm transforms a blurry image into a high-resolution image!
It can take a super low-resolution 16×16 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.

Click here for the PULSE code

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!

Click here for the OpenAI’s Image GPT code

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.

Click here for the DeepFaceDrawing code

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!

Click here for the PiFuHD code

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 the code available for everyone on their Github!

Click here for the RAFT code

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!

Click here for this Video Inpainting code

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.

Click here for the Old Photo Restoration code

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.

Click here for the MODNet code

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.

Click here for the DeOldify code

As you can see, this was an extremely insightful year for computer vision. I will be sure to cover the most exciting and interesting papers of 2021, and I would love it if you could take part in this adventure! If you like my work and want to stay up-to-date with AI technologies, you should definitely follow me on my social media channels.

Access the complete list in a GitHub repository

Spread the word

This post was originally published by Matt Mayo Editor at KD Nuggets

Related posts