TYLER ESSELSTROM

3D Artist - Technologist

[Iker J. de los Mozos @soyposmoderno]

My team at @Google has just open sourced GNM, our parametric 3D statistical model of the human head, which is learned from a large dataset of 3D scans. It provides fine-grained control over facial identity (170 head and 80 teeth components), expressions (383 components, with a range of -3 to +3) and head pose.

You can get all the data here! https://t.co/kj1vkbXR0x

Congratulations to everyone for the release, and stay tuned for the next ones ;-)

[(Alex) Compositing Academy @CompAcademyVFX]

A quick VFX Breakdown from a shot out of our newest project: THE RIDER

[Jeff Geerling @geerlingguy]

QuadRF is a phased array antenna that can see WiFi through walls, spot drones in the sky... and it's powered by a Pi 5 and FPGA board. Very neat device, we have a full video up on Geerling Engineering...

[Nick Stath @nickstath_art]

A little compilation of the 3D environments I designed for #AlienRomulis back in 2022.

These models formed the foundation for the concept art I produced during my time on the film.

#conceptart #Blender3D #cg

[Abby Welsh @DubThinkDev]

Fun fact: the Marathon spinner is actually a hand-coded shader! It has to display before the engine loads any textures or videos, so it's entirely procedurally animated and rendered by a shader I wrote for it using SDFs, procedural noise, and a pile of math for the animation :)

[Anderson Mancini @Andersonmancini]

React Three Fiber has had great text solutions for years… until you switched to WebGPU. There wasn’t a proper MSDF text component that worked with the new renderer, so I built one.

Introducing r3f-webgpu-text ✨
Example: https://t.co/shr5WE5uxF
NPM: https://t.co/5NliTWDA5i

MSDF text - WebGPU-first - Fast & lightweight - Familiar API

You can just:
npm i r3f-webgpu-text

Then:
<WebGPUText>Hello World</WebGPUText>

I hope it helps more people build with WebGPU.
#threejs #r3f #creativecoding

[Steven Cheng @stevencheng]

Years ago, my girlfriend worked in Yamaha's pick-and-place machine business. Even after we broke up, I still didn't really understand what a "pick-and-place machine" was.

Only recently, after discovering LumenPnP, an open-source pick-and-place machine, did I finally understand this fascinating piece of technology.

LumenPnP enables reliable and accurate assembly of electronic components onto circuit boards — bringing industrial SMT technology closer to the open-source hardware community.

The GitHub repo for this open-source pick-and-place machine is in the comments.

[Sean Bull Design @seanbulldesign]

Renault RS.26 Livery Concept

Back to some time sketching concepts

3D model licensed by @racesimstudio

#f1 #formula1 #livery

[亀井りく｜「RecGame」広��担当 @RecGame_RA]

【これ、リアルタイムで動いてます】
Overwatch 2に関わったPedro Borges氏がUE5で作ったトゥーンシェーダー。
セルシェーディングに手描き風のハッチングやモーションブラーを重ねて、
アニメがそのまま動いているような画になっています🎨
#UE5 #realtimeVFX

[Noah Verrier @NoahVerrier]

My oil painting of grilled cheese and tomato soup

[PeterTarka @PeterTarka]

Last year in renders

[Stuz0r @Stuz0r]

Strange Times
Created in Unreal Engine
Music from Soundstripe

[Yoshihiro Shibata @shiba_8ro]

サーボとネジと配線以外は3DプリントパーツなAIロボットアーム作ってます定期
https://t.co/0FDhYYODjH

[DFRobot @dfrobotcn]

An open-source robot vacuum you build yourself — Raspberry Pi, ROS 2, 2D LiDAR, Home Assistant, 3D printed chassis. No cloud, fully local.

oomwoo is early stage and building in public. The community can contribute modules in parallel — from SLAM navigation to dust bin design.

https://t.co/ip0HWptZg0

#ROS2 #RaspberryPi

[Ilir Aliu @IlirAliu_]

Forget lidar.
One single camera.
Runs in real time & is open source:

A streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences.

End-to-end.

Optimization tricks, cleanup steps?

Nope.

And it beats both streaming and even some offline methods.

Perception is becoming software-first.

Closer to machines that see and understand the world as it unfolds.

Thanks for sharing, @YinghaoXu1

📍Models: https://t.co/gnSDy919eX
Project page: https://t.co/zgpkgBvcik
Code: https://t.co/Js0MzHE387
Paper: https://t.co/FrzMojMMZC

——

Weekly robotics and AI insights.
Subscribe free: https://t.co/9Nm01QUcw3

[AK @_akhaliq]

Wan-Streamer v0.1

End-to-end Real-time Interactive Foundation Models

[invalidUsername.x @invalid_degen]

A WebGPU compute path tracer built from scratch.

Study #3

https://t.co/UZyj9ViJTw

- Multi-scatter sheen — SGGX microflakes + LTC (Zeltner, Burley & Chiang, 2022). Real fabric, with exact importance sampling.
- Sheen color + roughness textures
- No denoiser — raw, fully converged path tracing
- three.js + WebGPU

Paper: https://t.co/Lmm0puUNtA

@threejs
@thekhronosgroup
@webgl_webgpu
@WebGPU
@80Level

#pathtracing #pathtracer #ThreeJS #WebGPU #3D #gltf #khronos

[Mirza Beig @TheMirzaBeig]

fog -&gt; clouds

[Asad Memon @_asadmemon]

I have done it! Mighty's Batch-1 is in production! ✅

Mighty is the smallest VIO/SLAM module, here are the final specs and features:

- Global shutter camera + IMU
- 0.8W peak power
- Outputs pose @ 15hz, IMU runs @ 800hz
- Ultra efficient scalable loop closure and mapping via SDK
- Can sync multiple cameras thanks to new FSYNC pinout
- Connects to everything! Mavlink/CRSF for drones, Arduinos/ESP32, Phones, RPIs, etc.
- Powered by 5v USB or 3v-15v power input directly.
- Lua programmable, so you can change output protocols or add custom behaviors etc.

[Mirza Beig @TheMirzaBeig]

Raymarched depth blur pass. 🔍
&gt; fog transmittance as blend for blur.