{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiapkgd2zibhrtmkebq5i5oh4wshkzaub6myt5hhbkqrj7olfndn24",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmfa7joymt22"
},
"path": "/t/ai-in-game-development-gamedev-tips-tools-techniques-and-gpt-llm-agent-integration/1372841?page=4#post_102",
"publishedAt": "2026-05-21T19:14:48.000Z",
"site": "https://community.openai.com",
"tags": [
"Apple Machine Learning Research",
"HeadsUp: Large-Scale High-Quality 3D Gaussian Head Reconstruction from...",
"igl.ethz.ch",
"igl | Interactive Geometry Lab | ETH Zurich | Laplacian Surface Editing",
"igl | Interactive Geometry Lab | ETH Zurich | As-Rigid-As-Possible (ARAP)...",
"Avataaaaaar"
],
"textContent": "I am currently heading towards a video call avatar and I thought some of the stuff from that research might fit well for gaming as well. I mean most of it was made for gaming anyways…\n\nHere is a fresh one:\n\nApple Machine Learning Research\n\n### HeadsUp: Large-Scale High-Quality 3D Gaussian Head Reconstruction from...\n\nA scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Trained on 10,000+ subjects with state-of-the-art reconstruction quality.\n\n\n---\n\nAnd you should also watch out for the work of **Olga Sorkine-Hornung** and her work on:\n\n**Laplacian Mesh Editing**\n\nigl.ethz.ch\n\n### igl | Interactive Geometry Lab | ETH Zurich | Laplacian Surface Editing\n\nAbstract, paper, video, conference presentation and MATLAB demo.\n\nand especially\n\n**ARAP: As-Rigid-As-Possible Surface Modeling**\n\nigl.ethz.ch\n\n### igl | Interactive Geometry Lab | ETH Zurich | As-Rigid-As-Possible (ARAP)...\n\nAbstract, paper, video and other publication materials.\n\nThat stuff is patented by Disney afaik… so you may be careful how you use it - but on the other hand it is good to know none the less.\n\n\n---\n\nYou can connect your codex to blender (3D modelling tool) and then work on a so called mesh*\n\nAvataaaaaar\n\nHere are a few more words to feed chatgpt with:\n\nlandmark extraction, pose control, mimiks, phenoms and shape keys.\n\nIn that context adding that little background information about those techniques make alot of sense.\n\nHave fun",
"title": "AI in Game Development: Gamedev Tips, Tools, Techniques, and GPT / LLM Agent Integration"
}