yohawing (@yohawing) 's Twitter Profile
yohawing

@yohawing

Tech Art - Blender Unity Maya UE5 + α

ID: 358868391

linkhttp://yohawing.com calendar_today20-08-2011 16:54:39

10,10K Tweet

424 Takipçi

1,1K Takip Edilen

Tomohiko MUKAI (@tomohikomukai) 's Twitter Profile Photo

ジョイントベースでスキニングされたモデルに生じるめり込みを、スケルトンの姿勢補正によって解消する技術を発表予定です。CyberAgent AI Labの Takafumi Taketomi さんとの共著論文です。  ・project:mukai-lab.org/publications/e…  ・video:youtu.be/DKidf9pdEoI

Arseny Kapoulkine 🇺🇦 (@zeuxcg) 's Twitter Profile Photo

meshoptimizer 1.1 is out! Featuring two new major features, meshlet topology compression and opacity micromaps, as well as a few smaller features and improvements! Meshlet codec is heavily optimized for CPU decompression and output can be compressed further with Zstandard;

meshoptimizer 1.1 is out!

Featuring two new major features, meshlet topology compression and opacity micromaps, as well as a few smaller features and improvements! Meshlet codec is heavily optimized for CPU decompression and output can be compressed further with Zstandard;
CyberFox Agency (@cyberfox3d) 's Twitter Profile Photo

A few days ago I published a video about NVIDIA Kimodo. The big shift is that animation starts to be automatable instead of random. 🔹 Text prompt → motion 🔹 Pose lock → structure 🔹 Waypoints → direction That is the kind of control that makes AI animation useful in

yohawing (@yohawing) 's Twitter Profile Photo

ワンダリア横浜 ひたすらイマーシブシアター。 アプリでかざしながら回遊するだけ。 映像とアプリの作りは良かった。

yohawing (@yohawing) 's Twitter Profile Photo

Vive デザインにチャレンジしてるけど、いろいろ覚えること多い。 Token. DESIGN.md Figma MCP しばらくはFigma芸人になるぞ。

yohawing (@yohawing) 's Twitter Profile Photo

Saqooshaさんが作ってるClaudeCodeクライアントを使ってみてる。 軽量でサクサク使えていいかも。 github.com/Saqoosha/Canopy

Pierre-Antoine Bannier (@el_pa_b) 's Twitter Profile Photo

sam3.cpp - Meta's SAM 3 in pure C++ with Georgi Gerganov's ggml - Supports SAM 3.1, 3, 2.1, 2 and EdgeTAM - FP16, 4-bit quant (EdgeTAM in 15 MB) - Apple Metal GPU, CUDA, CPU - Text-prompted: "peach" → every peach - Single-file C++14 Performance-wise: - 100ms object detection,

yohawing (@yohawing) 's Twitter Profile Photo

Zed使ってるけど、人気になればなるほどIDEって重くなっていくよね…。sublimeが懐かしいよ。

Fadis (@fadis_) 's Twitter Profile Photo

NeuralPVS: Learned Estimation of Potentially Visible Sets : リアルタイム3Dグラフィクスに欠かせないオクルージョンカリングの新しい手法。シーンをFroxelに変換し、OA-CNNに各ボクセルが視点から見えるかどうかを判断させる dl.acm.org/doi/10.1145/37…

80 LEVEL (@80level) 's Twitter Profile Photo

.Move AI unveiled Genesis, its new high-quality markerless motion capture system, shifting from the consumer-focused Move Pro to a dedicated enterprise ecosystem. The system replaced action cameras with Z-Cam integration and a web environment with desktop:

Tengfei Wang (@dylantfwang) 's Twitter Profile Photo

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow

Yanpei Cao (@yanpei_cao) 's Twitter Profile Photo

Static 3D generation isn't enough. We need assets ready for animation. Our new #SIGGRAPH work, AniGen, takes a single image and generates the 3D shape, skeleton, and skinning weights all at once. Code is fully open-sourced! Kudos to Yihua and VAST AI Research 🧵(1/4)

yohawing (@yohawing) 's Twitter Profile Photo

これ、会社のプライベートネットワークを家も、含めてつくれるってことかな。 便利やんけ。