Mike Wong

Pixel-Space 👏

Preparing a major PR to improve @ThreeJS MaterialX support significantly. In order to perfect it, I've written an open source @MaterialXcg Fidelity Suite inspired by the @thekhronosgroup / @glTF3D fidelity tool: material-fidelity.ben3d.ca

Captured a vid of sampling a tiny diffusion model with the neural engine (A17 Pro) on my phone. Not very fast but pretty acceptable given everything happened on the iPhone locally

@jimmygunawanapp @Apple apple.github.io/coremltools/do…

@artixels @Apple How to make it running on ... say LocallyAI

☁️ Tiny diffusion model on @Apple iPhone Neural Engine (ANE) Converted one of my Tiny checkpoints into a CoreML package, and this image was generated in 3.78 seconds with memory use under 140MB on my iPhone 15 Pro. Local, private and energy-efficient 🥂

⛅𝐓𝐢𝐧𝐲 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 I trained before are fairly compact, the left on was from a 𝟗.𝟓 𝐌𝐁 one and the right was from a 𝟐𝟐 𝐌𝐁 one. It is fun to witness how a model learns the statistics which enables generative sampling of that photographic experience.

What I always wanted ! Pure JavaScript OpenEXR I/O Thank you @benhouston3d 🤩

@tiraoka *ARM64* 🤞

nightlyだけどsm121対応のtorchが来たっぽい。 forums.developer.nvidia.com/t/dgx-spark-sm… とりあえず、インストールしてVACEを試したところ、flash_attnで詰まったので、pipでflash_attnをビルドでインストール. 結果2%ほどの速度向上笑　ほぼ誤差？？　メモリは5%ほど少なくて済むようにはなった。うーんどうだろこれ

It's been a long time coming but the latest version of three-mesh-bvh brings support for out-of-the-box Line & Point cloud BVH support! Now all your geometries can be fast 🚀 1/3 #threejs #webgl #javascript

@ShinjiOgaki 👏 Merry Christmas 🎄

@artixels yes🙂

Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting TL;DR: How to freeze a dynamic molecular scene when people inevitably move. Contributions: • A Novel Problem Formulation and Benchmark: We are the first to formally address synthesizing high-fidelity, freeze-time videos from monocular MC footage, providing a new benchmark and evaluation protocol. • A Targeted Regularization Framework: We propose a novel method to identify and regularize hidden and defective Gaussians, the primary sources of temporal artifacts, anchoring them to reliable past or future states. • State-of-the-art Performance with Zero Inference Overhead: We improve visual quality and stability in existing methods without architectural changes. As the deformation runs only once for a target instant, we achieve inference speeds exceeding 280 FPS on an RTX 4090.

@lkwq007 😂

今年は2次元のtransient renderingを使った作品を提出しました。 運営の皆様お疲れ様でした。 #レイトレ合宿

The same stippling method can create some interesting depth of field effect.

Wow, a *phenomenal* single author paper by @ryichando ryichando.graphics

@voxagonlabs @BetterSoftwareC Finally watched your talk, very nice. Thank you for sharing 🙏

My talk from @BetterSoftwareC last week is up on youtube. I present my findings on thread synchronization and job systems that I learned while parallelizing the physics solver. youtube.com/watch?v=Kvsvd6…

@hardmaru @icmlconf LLM engineering 😅

ICML’s Statement about subversive hidden LLM prompts We live in a weird timeline…

🔥😍🔥