Our of our readers Chinito Pinoy has shared a pretty remarkable video with us that we would like to share. It is upscaling of sub HD resolution high-speed video at 240p, 480p and 960p from the Sony RX10 IV at 480 and 960fps and the A7S Mark III at 240fps from Sub HD to 4k UHD.
A few months back we took a look at Dain app, and how it was able to use AI and machine learning to create in between frames from almost any source footage and create something that looked and felt like real footage taken with higher fps cameras. The algorithm was so revolutionary that it took the world by storm, making older software that used re-timing from Adobe and others look antiquated and underpowered. The Dain-App was great and it was a pay what you want App but had an Achilles heel. The software required a powerful Nvidia GPU with as much VRAM as you could muster to be able to convert footage and re-time it.
The new Rife-App which is the direct successor of Dain App by the creator GRisk is up to 25x faster than the original, improves the algorithm, and by many examples betters it by creating more seamless transitions. The flow of frames is frankly jaw-droppingly beautiful, especially on low frame rate animation. We estimate that Animation studios in 2D will eat this app up immediately, and even 3D animation studios could reduce their render times by calculating fewer frames and using Rife-App to increase them to 24p, 30p or 60p from a lower source like 20fps or 12fps.
The Alice Camera, launched to great success this month has to be the most hopeful product for the future of cameras that we have seen lately. It marries the Sony IMX294, a 10.7 megapixel 4/3 sensor with a custom chipset including the Edge TPU chip from Google for AI and an FPGA for calculations. The result is a camera body with the same sensor as the GH5s which is a killer low light camera capable of excellent 4k footage and images with super low noise.
Then the camera back is attached to your Android or Apple smartphone to gain an interface and software to control it. The camera is capable of using the latest research for computational photography including HDR with multiple exposures merging, tracking, night mode, averaging of pixels, and as an open-source architecture, you can add features by other coders or your own to make the camera increase the feature set.
We just received a video link for a Raspberry Pi imaging platform that allows for 660fps slow motion video capture using the computing unit along with it’s memory and a $6 USD camera to record slow motion video with better than expected results. The video from 2019 by RobertElderSoftware explains the way the camera and R-Pi were able to capture the footage using some scripting and writing a windowed wide but not tall imaging rectangle directly to memory to create the cheapest slow motion camera.
Of note is the apparent low resolution of less than VGA at 640 x 64px and the somewhat appraisal of rolling shutter artifacts on some of the coins. However, RobertElderSoftware also has a step by step instruction video set on how to get a $40 Raspberry Pi computer and a $6 USD camera module to build your own homebrew slow motion camera with some scripting. After a lot of scripting and patience, you should be able to mimic his results.
Cheapest slow motion camera using a Pi Unit:
It is literally amazing what a dedicated engineer with an extremely limited set of tools and cameras is able to do on a project like this. Now imagine RobertElderSoftware using something like a more powerful ARM-based Mac M1 or similar with way more RAM disk for capture along with a better camera and sensor combination.
You can visit and subscribe to Robert Elder’s Channel here and learn many more from his cool projects and coding guides!
Maybe in the future, we could see some homebrew project kit that could be able to shoot 500fps or even 1000fps in 4k for a limited investment. In any case, we feel that you should take a look at the project below and get inspired. We thank our reader Nacho Simon for the heads up on this awesome project and Mr. Elder for his creativity and drive! -HSC
Video Sample and Step by Step Guides Below:
World’s Cheapest High-speed Camera For $6 With 660FPS!? by RobertElderSoftware:
Part 1) How To Record Video At 660 FPS On A $6 Raspberry Pi Camera – Part 1 by RobertElderSoftware:
Blackmagic Design has released Camera Setup 7.0 which upgrades the URSA Mini Pro 12k camera in several areas including improved frame rates at different resolutions. At 12k the maximum frame rate has increased to 75fps from 60fps and at 4k we now have up to 240fps in BRAW format from 220fps on a Super 16mm crop of the sensor. We also get 8k at up to 160fps from a maximum before of 110fps which is improved by leveraging the fast pipeline in the camera and delivering usable frame rates with good multiples.
While the camera is not cheap at $9,995, it is certainly a bargain considering the resolution and frame rates you have access to in BRAW RAW-Like format. It may be essentially the most powerful camera you can buy today for this price range and available with an F, EF, or PL mount the flexibility is there if needed. Blackmagic Design are also the owners of DaVinci Resolve and usually bundled it with their cameras. It makes for a hard to beat all in one system for shooting, editing, and postproduction. Dig in for more details…
Blackmagic URSA Mini Pro 12k – Full High Speed Frame Rates After Update:
12K 17:9 full sensor up to 60 fps
12K 2.4:1 up to 75 fps
8K DCI full sensor up to 120 fps
4K DCI full sensor up to 120 fps
8K 2.4:1 and 4K 2.4:1 up to 160 fps
6K Super 16 up to 120 fps
4K Super 16 up to 240 fps
Ursa Mini Pro 12K Unboxing & Footage by Epic Light Media:
We got over 20 messages with essentially the same video sample in our inbox this week. They all touted the new interpolation from the DAIN experimental App or (Depth Aware Video Interpolation App) which now analyses footage with a Neural network AI algorithm that crunches motion vectors and even what seemed impossible before “Object Occlusion” to generate higher frame rates from lower fps sources. The technology is pretty fascinating and should be further improved by more training and samples over the coming years.
For stop motion animators, this is a complete game-changer as now you could animate with as little as 8fps and then interpolate to 30fps or 60fps with very little in the way of tearing and artifacting as long as the footage is well lit and objects clearly defined. To make matters more interesting, it also analyses footage with shallow depth of field yielding impressive results.
Multiply Your Video Frame Rate with Interpolation or the “I” Word for Slow Motion Enthusiasts:
We visited the Interpolation topic in the past on our Fake Slow Motion article and concluded that then, the quality of interpolation while good was far from usable and you really could not compromise real high fps footage from interpolated versions except in very simple cases.
Now with DAIN technology, we have no choice but to re-visit the cases and analyze what it is capable of. We looked at a few dozen examples and it is clear the technology has progressed forward so much that now stop motion animation, 2D Cell-based cartoon animation, and even 3D animated sequences rendered at 30p can easily be turned in higher fps increments yielding impressive and in some cases miraculous results.
We would like you to first watch the video below to understand what a depth map is and how the software in DAIN can create frames from nothing that look just like real ones. A depth map will generate an approximated view of the world in a Lidar-Like vision representation to figure out to the best of the AI estimation where objects are in a scene according to their location close or far to the camera.
Depth-Aware Video Frame Interpolation by Wenbo Bao:
Even at 48fps from 12fps source, it is clear the technology in DAIN can yield impressive results even with heavy organic detail in the background including foliage. The software does an admirable job of estimating the relative position of objects in the video scenes.
AI使用フレーム補間アプリ DAIN APP byTALBOの実験室 Ch.: