3D Stereoscopic Photography – SPM/DMAG Free automatic depth map from stereo photos generation
http://3dstereophoto.blogspot.com/p/software.html
http://3dstereophoto.blogspot.com/2015/06/depth-map-automatic-generator-7-dmag7.html
Automatic depth map generation, stereo matching, multi-view stereo, Structure from Motion (SfM), photogrammetry, 2d to 3d conversion, etc.
Software to
– create depth maps from stereo pairs (stereo matching),
– generate intermediate synthetic views (lenticular),
– create depth maps from multiple views (multi-view stereo matching),
– create dense 3D reconstruction (point cloud) from multiple views (structure from motion and multi-view stereo),
– perform 2D to 3D image conversion (stereo conversion),
– perform edge-preserving smoothing,
– rectify/align stereo pairs
Epic Games to Pay Record $520 Million to Settle FTC Charges Over Child Privacy and Player Manipulation
“The Federal Trade Commission has accused the leading video game developer of manipulating young players into unintentional purchases, illegally collecting personal information of kids under the age of 13, and endangering children by connecting them with strangers in its hugely successful ‘Fortnight’ game.”
Cinesite group secures $235m funding package
https://www.televisual.com/news/cinesite-group-secures-235m-funding-package/
The Cinesite Group has agreed a new long term financial arrangement that ensures our ability to continue supporting our talent and customers across the world, which is a massive vote of confidence for the talent working within all the studios and what has been built within the Cinesite group
What is Neural Rendering?
https://www.zumolabs.ai/post/what-is-neural-rendering
“The key concept behind neural rendering approaches is that they are differentiable. A differentiable function is one whose derivative exists at each point in the domain. This is important because machine learning is basically the chain rule with extra steps: a differentiable rendering function can be learned with data, one gradient descent step at a time. Learning a rendering function statistically through data is fundamentally different from the classic rendering methods we described above, which calculate and extrapolate from the known laws of physics.”
How to learn to become a VFX artist
- Structure your learning time
- Consistency
- Retention
- Mental health
- Don’t feel intimidated
- Don’t feel rushed
- Be kind
- Luck is when preparation meets opportunity
Foundry Nuke Cattery – A library of open-source machine learning models
The Cattery is a library of free third-party machine learning models converted to .cat files to run natively in Nuke, designed to bridge the gap between academia and production, providing all communities access to different ML models that all run in Nuke. Users will have access to state-of-the-art models addressing segmentation, depth estimation, optical flow, upscaling, denoising, and style transfer, with plans to expand the models hosted in the future.
https://www.foundry.com/insights/machine-learning/the-artists-guide-to-cattery
https://community.foundry.com/cattery
A.J. Ghergich – MJ and Stable Diffusion 1.5 to imagine polaroids of superheroes in dive bars circa 1982
Prompt: Captain Marvel at dive-bar in 1982, polaroid, flash photo, ultra-detailed –q 2 –no hands –v 4
Former WarnerMedia CEO, Jason Kilar: Streaming Wars Will Produce ‘Multiple Business Casualties’ in Coming Years
“In this scenario, no more than three global entertainment companies are likely to attain the streaming-service scale required—300 million global subscriptions at an average of $15 per month—to generate attractive cash flows.”
Kilar made sure to note that he believes that Prime Video and Apple TV+ are exempt from this vision, as those streamers are both tied to giant tech and commerce companies with multiple revenue streams.
Scene Referred vs Display Referred color workflows
Display Referred it is tied to the target hardware, as such it bakes color requirements into every type of media output request.
Scene Referred uses a common unified wide gamut and targeting audience through CDL and DI libraries instead.
So that color information stays untouched and only “transformed” as/when needed.
Sources:
– Victor Perez – Color Management Fundamentals & ACES Workflows in Nuke
– https://z-fx.nl/ColorspACES.pdf
– Wicus
chat.openai – A conversational AI system that listens, learns, and challenges
https://openai.com/blog/chatgpt/
Tell me about when Christopher Columbus came to the US in 2015
This question is a bit tricky because Christopher Columbus died in 1506, so he could not have come to the US in 2015. But let’s pretend for a moment that he did!
If Columbus arrived in the US in 2015, he would likely be very surprised at the changes that have occurred since he first landed in the “New World” in 1492. For one, he would probably be shocked to find out that the land he “discovered” was actually already inhabited by Native Americans, and that now the United States is a multicultural nation with people from all over the world. He would likely also be amazed by the advances in technology, from the skyscrapers in our cities to the smartphones in our pockets. Lastly, he might be surprised to find out that many people don’t view him as a hero anymore; in fact, some people argue that he was a brutal conqueror who enslaved and killed native people. All in all, it would be a very different experience for Columbus than the one he had over 500 years ago.
