Benjamin Bojko

Technology Director at @Bluecadet. I make things that weave digital storytelling into physical experiences.

|

[Benjamin Bojko @benjaminbojko]

Incredibly well visualized explainer of splines and continuity by @FreyaHolmer: https://t.co/xaMElNC31I

This makes smooth movement and rendering in 3D so much more clear to me.

[Benjamin Bojko @benjaminbojko]

Week 3 with #ableton and #touchdesigner: Effects. I wanted something drone-y and rumbly, that I could visualize as vibrations. For the visuals I experimented with instancing and shading. Very happy with how this track turned out.

https://t.co/UIJlioqcJz

#creativecode

[Benjamin Bojko @benjaminbojko]

Avalanche is already being used in TV broadcasts, and I could see this bringing a big boost to Unreal Engine in the experiential installation space, especially for content- and UI-focused experiences. Very excited to try this out, hopefully with UE 5.4.

[Benjamin Bojko @benjaminbojko]

Epic's new Project Avalanche looks like the closest thing to recreating what I loved about Flash: Real-time 2D/3D/vector graphics with a powerful timeline, blend modes, motion tools and more.

https://t.co/oT41iv9PGf

[Blair Neal @laserpilot]

I recently compiled my 2022 Survey of Alternative Displays (covering over 30 display types) into a ~125pg PDF for sharing/archival/printing purposes - you can grab it here: https://t.co/yAZvdlboAk

[Benjamin Bojko @benjaminbojko]

Week 2 with @Ableton & @1null1: basic chord progressions over drums and ocean sunrise inspired visuals. Dug into basic music theory, scales and chords, and MiniLab 3. In TD explored height maps, noise, and basic signal processing.

#touchdesigner #creativecodeart #ableton

[Benjamin Bojko @benjaminbojko]

Week 1 of Ableton + TouchDesigner: I joined a audio + visual study group and our first week's focus was drums. I challenged myself to stick with a simple loop and square to see how much I could express each drum.

#ableton #touchdesigner

[Jason Key @key_vfx]

🌊🎸🔊 #EmberGen

[Javi Lopez ⛩️ @javilopen]

🔴 Finally! NVIDIA has finally made the code for Neuralangelo public!

It has the ability to transform any video into a highly detailed 3D environment, and it's a technology related to but DIFFERENT from NeRF.

💡 Here's how it works:
It takes a 2D video as input, showing an object, monument, building, landscape, etc., from various perspectives and analyzes details such as depth, size, and the shapes of objects.

From this, the AI sketches an initial 3D model, similar to how an artist molds a figure. This representation is then refined to highlight more details, just as an artist would make the final touches when sculpting.

The result is a 3D environment/model, perfect for use in any environment.

Imagine the applications it will have for video games, cinema, virtual environments, VR, and more! 📽️🎮

💡 More details: A year ago, an article was presented on a groundbreaking technique called NVIDIA's Instant NeRF. This technique turns images into stunning 3D scenes in a short time, ideal for creating realistic models for video games and other applications. Although Instant NeRF had a lot of potential, the generated models were not perfect and often lacked detailed structures, appearing somewhat cartoonish.

A year on, NVIDIA releases a new technique based on Instant NeRF, named Neuralangelo. This enhances the fidelity of surface structures. While NeRF reconstructs real objects in virtual environments from images or videos, Instant NeRF speeds up this process, and Neuralangelo further improves the quality, making the generated objects appear even more realistic when examined up close.
Neuralangelo improves Instant NeRF's approach in two key ways related to the hash grid encoding technique:

1⃣ Numerical gradients have been used to compute higher-order derivatives as a smoothing operation. This optimizes the "hash grid" encoding using numerical rather than analytical gradients, providing a smoother input to the network that produces the 3D model.

2⃣ A "coarse-to-fine" optimization has been implemented in the hash grids to control different levels of detail. That is, they first focus on a smoothed version of the scene, and then refine it with more detailed updates.

Well, as Arthur C. Clarke said, "Any sufficiently advanced technology is indistinguishable from magic."

[Benjamin Bojko @benjaminbojko]

NeRFs are amazing ways to capture 3D scenes, but displaying them natively and in real time is still a challenge. This is a really impressive paper + code with a path towards real-time, high-quality rendering: https://t.co/IqHYADnLQ9

[Benjamin Bojko @benjaminbojko]

Example posted above used the large model, default decoder/settings and the prompt "A warm, minimalist ambient track with strings, flicker and base"

[Benjamin Bojko @benjaminbojko]

I've been testing FB's new #AudioCraft models today and have been pretty impressed so far. Excited to explore how this could be used in more dynamic ways for media installation soundscapes.

[Benjamin Bojko @benjaminbojko]

- The larger the model, the more stable the track (less distortion)
- First 20-30s are usually solid, then tracks gradually distort
- 16GB GPU is recommended, but my 12GB 3080ti generated ~140s audio with the large model
- Generating 1s of audio took about 3s avg

[Benjamin Bojko @benjaminbojko]

@vanschneider @MITMuseum Thank you! So wild to see the amount of progress made in the field. Still, old design challenges and affordances remain. People need an intuitive and safe space for writing, even if it's assisted by an AI 🤖🤝🧑

[Benjamin Bojko @benjaminbojko]

New article on how we designed a physical human x AI poetry experience for @MITMuseum: https://t.co/8Y7O54qgQ1. With #chatgpt3 and davinci-003 out, it was great to reflect on the affordances of text AIs and how far those have come since GPT-2🤯

[Benjamin Bojko @benjaminbojko]

The MIT Museum recently opened and I got to lead creative tech for media across the four major galleries. Learned so much about AI, spatial integration, computation, gene editing, hologauze, curved OLED benders, milling and more. https://t.co/efjrrNJM9j. More insights to come

[Benjamin Bojko @benjaminbojko]

Headed to Pittsburgh for #ASTC2022. Come say hi if you're around! I'm presenting a sneak peek at our recent work for the @MITMuseum at 1pm on Monday: Beyond Science Lessons, Towards Science Experiences

[Benjamin Bojko @benjaminbojko]

@davidnunez Damn. So sorry to hear this, David. Sending big hugs to you and the family.

[Benjamin Bojko @benjaminbojko]

@halfpennyr @jodiem @LDNsCall So glad it's proving to be helpful!

[Benjamin Bojko @benjaminbojko]

Tensorflow in Cinder? @shiweili did a write up on how to get a DLL + lib compiled, GPU acceleration and all: https://t.co/EPbgyfKXwf. Cinder block hopefully to follow soon.