AI Video Editing Blog

CONTENTS: Watch Tutorial | Key Points

Learn how to add some EPIC to your videos with this easy to learn masking technique.

https://player.vimeo.com/external/435115275.hd.mp4?s=21bf40d5ce3f3dbed84f461a8a99841a8931173e&profile_id=175

2020 was the year of virtual insanity. On-demand streaming skyrocketed, everyone wanted to Zoom and even Gordon Ramsey started dancing on TikTok. Yes, things got weird.

The world was officially on lockdown and ”bored in the house-bored in the house bored.” This was a great time to get creative! So, I decided to get some fresh air and do what every video editing Jedi does on their break…dance in the street to a Jamiroquai classic of course .

Let’s learn some masking

I created this video in After Effects, but you can do this in Premiere Pro or any other editing program you prefer. Please watch the tutorial below and follow along as we take a deep dive into all things nerdy.

Tutorial Key Points

1. Plan ahead: I believe this is a relatively easy technique for you to learn, even if you are just starting out in After Effects. However, take some time to really block out your shots. Get creative—have some interesting actions you can perform to make your video stand out from the rest. Editing really is easy the part.

2. Duplicate and Freeze: Once your footage is on the timeline, duplicate that layer (Ctrl+D for PC & Cmd+D for Mac). Right-click the duplicated layer on your desired frame, head up to ”Time” and select ”Freeze frame”

3. Pen and Zoom: The duplicated layer will now be frozen. It’s now time to put the work in my friend, this part will take some time. Head up to your tools, select the pen tool and start drawing a mask around your subject. Be sure to really zoom in for this. Use the hand tool/spacebar to help you navigate the screen.

4. Trim and Repeat: Once the mask has gone full circle, you should be able to see the original below it. Now, trim the duplicate layer from the point you want it to dissapear (Ctrl+Shift+D for PC & Cmd+Shift+D for Mac). Play back what you have so far and watch your progress. Make adjustments if need be & get ready to it all over again.

Always duplicate from your first layer (the unfrozen layer).

5. Mind the gaps: Make sure you also mask out the sections that reveal the unfrozen layer. Select the frozen layer again and draw another mask. This should automatically display as another colour. Click the drop-down on that layer to reveal the masks, head to the second mask, select the ”Add’ drop-down and choose ”Subtract”.

6. Change to square: The last thing I did to make it pop was change the aspect ratio of my final edit from 16:9 (1920×1080) to 1:1 (1080×1080). This allowed me to just keyframe the position of the video from left/right and even zoom in/out for that dolly motion effect. This is the secret to the magic! You can even add some fake camera shake on there—just play and have fun with it.

That’s it! Try it out and don’t be afraid to push it further: innovate, get creative. Please share with us what you come up with, we’d love to see it .

Did you find this post helpful? Please drop us your thoughts in the comments below and consider subscribing to our YouTube channel for more helpful tips and tricks on how you can get more and better video done, faster.

About Us: Kamua is a technology startup headquartered in London with engineering operations in Bucharest. With Kamua you can cut, crop and repurpose videos faster, all in a browser, assisted by our AI.

High-speed, browser accessible tools with smart automation for intelligently reframing video.

https://player.vimeo.com/external/392970914.sd.mp4?s=2a0172a8b930cebd302864dd7f1580a76d982588&profile_id=165

Comparison of Google AI’s AutoFlip to Kamua’s AutoCrop and a static Center Crop with no AI tracking.

One of the biggest challenges that video storytellers face in 2020 is taking video filmed for desktop and converting or “reframing” it for mobile portrait apps such as TikTok, Snapchat and Instagram. Spending countless hours dragging boxes around in buggy desktop software packages and waiting for projects to render is the usual grind that creators tell us about. That’s why we built Kamua.

Kamua is designed from the ground up to operate 100% in the cloud using the fastest GPUs available and uses no local computing resources. This results in huge reductions in manual workflows, saving countless hours for creative people. We have users who have cut manual workflows from 16 hours to 15 minutes by embracing the automation we have built over the past three years.

“Kamua has transformed our team’s ability to quickly produce social videos for our clients based on their broadcast TV ads. We cut our end to end production time by over 90% and we now produce multiple variants to A/B test, something we did not have the time to do before.”
– Kamua trial user

https://player.vimeo.com/external/392973964.sd.mp4?s=c130ef38928edf105fc6f1be6aae6866d4a76abb&profile_id=164

Kamua’s AI detects and tracks objects and uses machine learning to simulate how a videographer would have filmed the shot. This saves video storytellers critical time and frustration, and frees up them and their hardware to create more.

Kamua offers a wide range of features focused on time savings and ease of use. Cloud-based computing renders video outputs in minutes instead of hours; gone are the 200-hour learning curves that traditional editing software apps often require users to go through to become proficient in the kinds of editing techniques needed for professional social video creation. This approach empowers content marketers to produce professional grade results themselves and frees up video editors to focus on the nuances of storytelling.

How Does Kamua compare to Google AI’s AutoFlip?

Last week, Google AI released something they have been working on for some time: a machine learning based video reframing technology called AutoFlip. When we saw that blog post, we were pretty shocked to see that Google has been working on almost exactly the same approach to reframing and shot detection that we had developed — and they had decided to open source their framework.

“As an early-stage startup, you would never assume your AI video tech is better than Google’s stealth tech; all you really know is how hard it has been to build your tech.”

We installed AutoFlip and ran it on a set of videos, multiple times. It’s not easy to write a blog post with a section about how your own startup is better than Google without seeming like braggarts…but Kamua is not just a bit better than AutoFlip, it’s much better. Possibly an order of magnitude better and faster. And it’s already deployed and accessible in a browser. As an early-stage startup, you would never assume your AI video tech is better than Google’s stealth tech; all you really know is how hard it has been to build your tech and, now, you also know that it’s market ready.

We detect and track objects in video better, we have multiple neural networks that collaborate to determine what the focal points of videos likely are, not just object detection, and we have better camera smoothing and pathing, to name a few.

We are sure that by open-sourcing their code, Google will see improvements to AutoFlip, but they are not open-sourcing some critical technologies that are in their (paid) Google Video Intelligence API. That makes it more likely that Google is using AutoFlip to generate use cases and data for Mediapipe, rather than trying to make AutoFlip part of a cloud product suite, but we don’t know and time will tell. What we can be 100% sure of is that Google recognises the huge demand for this kind of technology, has worked very hard, and if they are saying it’s important, we’re probably ready to launch at exactly the right time.

So, this week we decided that it’s time to let everyone know that they can access Machine Learning based video editing technology right now in a browser.

https://player.vimeo.com/external/392947337.hd.mp4?s=630537198fcb79ac51e67c8ca6643657bac7783c&profile_id=174

Kamua isn’t just a bit better than Google AutoFlip; it’s miles ahead.

How Kamua Works

We built and trained several different neural networks to replace the most monotonous and low added value tasks that video editors begrudgingly carry out every day.

Finding Cut Points in videos
Cropping videos from Landscape format to Portrait and Square
Re-arranging the order of scenes or shots in a video

https://player.vimeo.com/external/392970783.sd.mp4?s=5984af2c9a01c88dbebb6a9d5489c655f28bc339&profile_id=164

Kamua’s proprietary AutoCut technology cuts videos into their component shots with no user intervention or threshold setting.

The user has the option of fully automating each process or manually intervening to override the decisions of the AI on a shot-by-shot basis. An example of this is the ability to instruct the AI to choose different objects, people or elements to focus on for the crop.

https://player.vimeo.com/external/392971006.sd.mp4?s=aaccf33b29db609331f7e45a1378f4503b7f3a7f&profile_id=164

Kamua’s CustomTrack technology allows the user to click and drag a selection box around the object or area on which they wish to focus the crop.

Bleeding Edge Browser Tech

All a user needs is Google Chrome or Firefox (full Safari support coming soon) on a laptop and a wi-fi connection. Videos can be linked directly from a hosting source (such as YouTube or Vimeo) as long as the user has the rights to use the source videos, or uploaded by the user. It takes 20 minutes or less to learn how to use Kamua’s core features, whether a user has previous editing experience or none at all. Kamua pushes the limits of browser video seeking, playback and audio file management and we are excited to see how powerful they are becoming. We also plan to release mobile apps in the coming months.

Choosing different aspect ratios is as simple as clicking a drop-down menu or setting a custom value. Rendering currently takes 0.5s per second of source video footage, and the video renders in its original resolution.

Future & Experimental Features

https://player.vimeo.com/external/392970950.sd.mp4?s=3c2cf520f5e6824300559e80ce0dee2bec22fd66&profile_id=164

Kamua will soon offer users experimental features such as Contextual Object Removal.

Deep Learning gives us incredible opportunities to offer game-changing technology to video marketers. In this rather impractical demonstration, we show how this technology can perform complex tasks such as removing the bicycle, the rider and (most of the) shadow from the scene. As the machine learning improves, it will be able to more accurately re-paint the areas that were previously obscured by the removed object.

This technology does become practical for the removal of hard-baked subtitles, graphics and other items that do not fit within a cropped video on a mobile screen, or that need to be removed or replaced.

We are also working on a variety of additional features, such as automated upscaling (480p to 4K), colorization, and color matching. Subscribe to our blog here to stay up to date.

We will be publishing more posts in the coming weeks and months that go into our tech and product in greater detail, and our YouTube channel already has some informative tutorials and demos on it. We hope you will subscribe and look forward to your feedback in the comments.

Full disclosure: Google nominated Kamua to its Google Cloud for Startups program, allowing us to operate class-leading GPU servers and deliver Kamua’s AI to our Beta testers since August 2019.

About Us: Kamua is a technology startup headquartered in London with engineering operations in Bucharest. We are hiring. Follow us on LinkedIn and check out our job postings there.