arpu (@arnputz) header
arpu (@arnputz) profile picture

https://nitter.cf/t.co/G8rq3E1397 https://nitter.cf/t.co/MC95Bj4G4l

Wien, Österreich
Joined March 2016
Photo by arpu (@arnputz)Photo by arpu (@arnputz)Photo by arpu (@arnputz)Photo by arpu (@arnputz)Photo by arpu (@arnputz)Photo by arpu (@arnputz)Photo by arpu (@arnputz)Photo by arpu (@arnputz)Photo by arpu (@arnputz)Photo by arpu (@arnputz)
oh btw, THREE.EnvironmentShadowLights: npmjs.com/package/three-envi… For those few poor souls tired of setting up @threejs lights to match environment map by hand 🤲💀
6
4
49
3,491
mobile-friendly 5.5GB OpenVDB, available now through your nearest @threejs provider 🙂‍↔️ Live: mjurczyk.github.io/openvdb/ (0.5.x) 5.5GB down to 3 streamable LOD levels: LOD0 1.5MB (near-instant) LOD1 8MB (mid-ground) LOD2 50MB (as detailed as web reasonably needs)
3
4
16
1,126
arpu retweeted
There's a lot of AI hate on @pouetdotnet lately, so I decided to vibecode a demo about it. 💾 xplsv.github.io/lolfuckai/
23
10
2
172
10,901
arpu retweeted
We just open-sourced the world's fastest WebGPU kernels for 200+ machine learning operations. Specialized for your hardware. They run entirely locally in your browser. Now available on Hugging Face 🤗 Tell your agent to use @huggingface/kernels in your next project.
15
63
5
466
21,795
I’m having AI port Three.js and its examples to Rust + WebAssembly for various experiments. github.com/takahirox/three-r…
1
13
686
🔥🏆Heat Kernel Textures (HKTex) received the Best Paper Award at #ECCV2026. 🏆🔥 UV-mapping anchors 3D texturing to the past. Inspired by 3DGS, we rethink textures using heat kernels and NO splatting! circle-group.github.io/resea…
5
32
2
192
19,804
After more testing this is what I'll use for Basis Universal's PBR material support: a PCA-based or bilinear model. Way faster to decode vs. MLP (neural) and not need a GPU or even SIMD. We can already encode to full BC7/ASTC in real-time (~8 threads=1 gigatexels/sec.).
If the big win from neural texturing is saving VRAM, there are lots of ways to do that by creating your own non-neural custom texture formats, and doing mipmapping/filtering yourself. Then: no neural-specific IP concerns. Decoding is also fast/simple. I'm using the same ES training code I wrote for neural nets but with a bilinear model. The decode cost: 60-250 weights.
2
1
5
875
You don't need neural networks (at all) to compress PBR material textures. PCA applied to texture/image data is old prior art. The lower dimensional data is easy to handle. "Dimensionality reduction for image and texture set compression" by Bart Wronski bartwronski.com/2020/05/21/d…
2
3
7
856
Equal Earth projection is coming to 3DTilesRendererJS! 🗺️ Here it is rendering TerrainRGB & vector annotations. The LA streets look a bit less square but the projection looks great! We are updating the engine so data aligns across projections, letting you render maps in three.js however you need ✨ #equalearth #GIS
NEWS 🚨: The UN has voted 164 to 1 to adopt a new world map that shows countries at their true relative sizes, with the United States the only country voting against it Before (left) and New map (right)
6
4
40
3,991
Fitting a neural texture decoder with ES (no backprop): richg42.blogspot.com/2026/09…
2
4
848
arpu retweeted
Furry objects render beautifully in NeRFs but crumble in real-time graphics. This method replaces volumetric blobs with explicit, anti-aliased line segments for hair and fur that rasterize, shade, and simulate properly. 📄 arxiv.org/abs/2609.00625v1 🌐 kenji-tojo.github.io/sa26-li…
4
10
1,197
Grok: "Encoding *through the filter* lets the codec spend bits on interior detail instead of fighting seams." Note none of this work is theoretical. We have billions of ASTC decoders in hardware right now, and we have the software to unlock these large block texture units. github.com/BinomialLLC/basis…
ASTC LDR 12x12 without and with in-loop deblocking: 5 tap pixel shader (or applied during transcoding to BC7 etc.), Stochastic Coordinate Descent (SCD) during encoding. Same texture data on each side. In-loop deblocking unleashes the largest ASTC block sizes.
2
5
941
It's on the list. Enable it in filters :) A ready to use link: bughunt.productcompass.pm/?r…
4
2
10
9,092
arpu retweeted
if you ever have to read, debug, or hand-write SDP, try explainer.pion.ly/ It's an interactive SDP explainer and debugger built by @supadotsh Great for debugging WebRTC, SIP, RTSP, or just finally learning what every SDP line actually does.
10
1
30
2,924
A GPT-3 moment for robotics⚡️ The first time it hit me was watching a Skild robot make pancakes, after seeing it done just once. It had never been trained on pancakes before. One Skild Brain: - doing tasks far OUTSIDE its training distribution from a single video prompt, with no task-specific fine-tuning - executing 10+ min long-horizon tasks - capable of instruction following They have cracked in-context learning💥 The era of general-purpose robot intelligence is just beginning
Introducing S1, our new foundation model that learns from one example. It can be taught 10-minute long tasks that it has never seen before, from one video prompt without any fine-tuning. Watch S1 operate in real-time via in-context learning:
5
10
1
110
19,168
Three.js + KHR_interactivity demo github.com/takahirox/threejs… #threejs
1
8
535
arpu retweeted
Pick one:
42%Claude
36%Codex
7%Gemini
15%Grok
1,812 votes • Final results
36
9
3
70
20,351
arpu retweeted
Playing around with pushing Three.js WebGPU further. Three.js stays in JS running through Node, while the rendering is passed down to C++ using Vulkan + RTX. Now testing native ray-traced reflections, hit radiance and lighting. Still experimental, but pretty happy with how far this has come so far.
13
12
4
203
19,936
Depth-aware light injection in TypeGPU I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step Inference, lighting and draw all go through the same command encoder.
955
4,651
1,285
49,788
10,119,530