arpu

3.2K posts

arpu banner
arpu

arpu

@arnputz

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

Wien, Österreich Katılım Mart 2016
3.1K Takip Edilen551 Takipçiler
arpu
arpu@arnputz·
@isaac_mason_ do you generate the glb collider from the spz automatic?
English
1
0
0
17
robot
robot@alightinastorm·
I vibe coded a ThreeJS world editor with GPT 5.4 in 48 hours from scratch Open Source, MIT Features: - Integrated AI texture generation - AI model generator - Vertex/Edge/Face Editing - Physics and a Player Controller to test the world - Export (glb) - Pretty much everything essential trenchbroom and hammer offer (brushes, presets, extrude, arc, fill, flip normals, material browser, inflate, deflate,...) - Split View (2D orthogonal) yes, that is dust2 enjoy 😊
English
34
35
480
53.3K
takahiro(John Smith)
takahiro(John Smith)@superhoge·
Many enemies in Hytopia open SDK fork + Three.js! Anyone wants to play this game on your web browser? I may publish if you want soon!
English
10
10
67
6K
Marques Brownlee
Marques Brownlee@MKBHD·
$599 starting price for Neo. I’m getting hands on today. Ask me anything
English
2K
415
21.9K
1.5M
arpu retweetledi
▣ P.A.T.H.
▣ P.A.T.H.@materializepath·
what if three.js scenes had a real DSP brain? replaced basic Web Audio nodes w/ a Faust sound engine: DSP → WASM → browser codex & i built a custom web ui control surface to play & tune drone + fx dsp params before mapping them to three.js visuals next post i'll share full interactive #threejs experiment #faust #webaudio #dsp
English
1
1
6
1.2K
avaer
avaer@aitheologian·
WebSR is neat, 2x your anime 1024 for 11-20ms on laptop. Sizeof weights will make you rethink your life. Not really worth it on framebuffer hotpath but considering halving asset res...
avaer tweet mediaavaer tweet media
English
1
0
0
166
arpu retweetledi
Red Hat AI
Red Hat AI@RedHat_AI·
vLLM v0.15.0 project update is out. In this 15-minute update, @mgoin_ shares: 🆕 What’s new in vLLM v0.15.0 🪲 Debugging a real memory leak in vLLM 🧩 Mixture-of-Models on AMD GPUs with vLLM-SR 🧠 New model support: DeepSeek-OCR 2, Kimi K2.5, Arcee Trinity-Large, Qwen3-ASR
English
2
14
161
7.5K
arpu retweetledi
rsasaki0109
rsasaki0109@rsasaki0109·
CuMesh: High-Performance Geometry Processing for PyTorch Cuda mesh utils. github.com/JeffreyXiang/C… CuMesh is a GPU-accelerated library designed for high-performance 3D geometry processing directly within the PyTorch ecosystem. It provides efficient primitives for mesh cleaning, decimation, remeshing, and UV unwrapping. Key features include: ・CUDA-Accelerated Mesh Operations: Fast topology queries, simplification, hole filling, and cleaning. ・Remeshing: Remesh arbitrary meshes using narrow-band UDF and Dual Contouring. ・UV Unwrapping: Efficient UV parameterization with xatlas enhenced by a fast mesh clustering on the GPU.
English
2
31
182
11.1K
arpu
arpu@arnputz·
@richgel999 next is GLTF extention and ktx2 support
English
0
0
0
29
arpu retweetledi
Richard Geldreich 🇺🇸
Richard Geldreich 🇺🇸@richgel999·
Basis Universal v2.0, our GPU supercompressed texture library, is now live on GitHub. This update adds full ASTC LDR and supercompressed XUASTC LDR (supporting all 14 ASTC block sizes) with Weight Grid DCT, and new real-time Analytical BC7/ETC1 encoders. github.com/BinomialLLC/ba…
English
4
5
25
3K
arpu retweetledi
La Silla
La Silla@TheChairNerd·
With the help @aframevr I dusted off my old daylight system component and turned it into a nice 360 32-bit panorama exporter. Sun size, 8k, artificial lights, night sky and other cool updates are on the way! Start making you own hdri panos here! ex3d.com/hdri @kfarr
English
2
3
10
574
Overworld
Overworld@overworld_ai·
@kalin_t It is open source :) Apache 2.0
English
1
1
24
2.6K
Overworld
Overworld@overworld_ai·
Today, we’re releasing a research preview of our real-time, local-first world model built for interactive, playable AI-worlds 60fps, locally run, all on consumer-grade hardware. Come take a look ⬇️
GIF
English
56
155
1.1K
495.1K
arpu retweetledi
Pablo Vela
Pablo Vela@pablovelagomez1·
I've been working a lot with SAM3 and the Momentum Human Rig (MHR). I finally integrated it into the data I'm working with @rerundotio. The progression I've taken looks as follows SAM3 + SAM3D-body on 1. a single image 2. a set of multiple images 3. a single video 4. A multiview video capture I took inspiration from the SAM3D-body paper and built a multiview fitting optimization pipeline. This pipeline involves using the 2D keypoints from the single-view pipeline, triangulating them, and employing an L1 loss between the 2D/3D keypoints. The temporal stability isn't great, so that's the next portion I'm going to focus on. One really frustrating thing about SAM3D-body is the lack of per-joint confidence values. It makes it harder to deal with occlusions. I'm probably going to need to use a separate model, or maybe add a confidence head.
Pablo Vela@pablovelagomez1

Back to working on exo + ego in @rerundotio. This is a big jump in progress! One of the main painpoints I've had is getting the ego and exo views aligned in the same coordinate system, but I finally managed to get it all working. This means that now I have 1. Slam working for ego 2. Calibrated exo views 3. 3D keypoints for the full human body 4. 6DoF wrist poses 5. Temporally aligned videos 6. Spatially aligned multi cameras Now it's time to scale it up 🙂

English
9
43
448
42.3K
Ziqi Huang
Ziqi Huang@ziqi_huang_·
To tackle 𝘎𝘦𝘯𝘦𝘳𝘢𝘭𝘪𝘻𝘢𝘣𝘭𝘦 𝘔𝘰𝘵𝘪𝘰𝘯 𝘎𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘰𝘯 🕺, 𝗩𝗶𝗠𝗼𝗚𝗲𝗻 systematically transfers knowledge from ViGen -> MoGen across three pillars: Data, Model, and Evaluation. 📜 arxiv.org/abs/2510.26794 💻 github.com/SMPLCap/ViMoGen 🌐 linjing7.github.io/vimogen/
Ziwei Liu@liuziwei7

🚀The Quest for Generalizable Motion Generation🚀 #ViMoGen systematically transfers knowledge from 🎬Video Generation🎬 to 🏊‍♀️Motion Generation🏊‍♂️ across three key pillars: data, modeling, and evaluation - Project: linjing7.github.io/vimogen/ - Code: github.com/SMPLCap/ViMoGen 📜ViMoGen-228K @huggingface: huggingface.co/datasets/wruis… 📊MBench: huggingface.co/spaces/wruisi/… . Thanks to @_akhaliq!

English
2
18
120
11.4K
arpu
arpu@arnputz·
@garrettkjohnson @onirenaud Can you point me in the right direction? goal is to have a collider mesh for physics on the Gaussian Splats
English
1
0
0
40
Garrett Johnson
Garrett Johnson@garrettkjohnson·
cc @onirenaud - you could create a custom BVH for your Gaussian Splats if you want to accelerate raycasting or other kinds of queries for things like collisions. Would be cool to see a demo for that if you want me to point you in the right direction.
English
3
0
9
1.2K
Garrett Johnson
Garrett Johnson@garrettkjohnson·
With the new abstractions in three-mesh-bvh, making a custom BVH is easier than ever! SkinnedMeshes can now have one created directly, leading to an over 2x perf improvement on update vs creating a new static mesh. 🚀 What else needs a BVH? 1/2 👇 #threejs #webgl #gamedev
English
6
39
329
21.7K
Software Mansion
Software Mansion@swmansion·
TypeGPU 💜 @threejs TypeGPU 0.9 can integrate with Three.js Shading Language (TSL) on a very granular level, thanks to the @typegpu/three package. So now, you can write shaders in TypeScript while leveraging the rich Three.js ecosystem! To showcase the integration, we prepared docs and ported a handful of official Three.js examples 👇
English
8
77
685
42.5K