Keep on to blur preview images; turn off to show them clearly
![[ Siggraph Asia '25] DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting
Contributions:
1. We propose an optimization framework that incorporates a gradient diffusion strategy, enabling large-step vertex updates while maintaining mesh regularity.
2. We introduce a postprocessing pipeline that extracts high-fidelity surface attributes—diffuse, normal, and displacement maps—directly from the optimized Gaussian splats.
3. We demonstrate that our structured Gaussian representation achieves high-quality geometry reconstruction and supports downstream applications such as editing, cross-object manipulation, and rendering.](/_next/image?url=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F1999386488317050882%2Fimg%2FqxjIuwTMbE6Qq1ad.jpg&w=3840&q=75 "[ Siggraph Asia '25] DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting
Contributions:
1. We propose an optimization framework that incorporates a gradient diffusion strategy, enabling large-step vertex updates while maintaining mesh regularity.
2. We introduce a postprocessing pipeline that extracts high-fidelity surface attributes—diffuse, normal, and displacement maps—directly from the optimized Gaussian splats.
3. We demonstrate that our structured Gaussian representation achieves high-quality geometry reconstruction and supports downstream applications such as editing, cross-object manipulation, and rendering.")
[ Siggraph Asia '25] DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting Contributions: 1. We propose an optimization framework that incorporates a gradient diffusion strategy, enabling large-step vertex updates while maintaining mesh regularity. 2. We introduce a postprocessing pipeline that extracts high-fidelity surface attributes—diffuse, normal, and displacement maps—directly from the optimized Gaussian splats. 3. We demonstrate that our structured Gaussian representation achieves high-quality geometry reconstruction and supports downstream applications such as editing, cross-object manipulation, and rendering.
Paper: https://t.co/F184dLiEOE Project: https://t.co/E7nqCAiY39 YouTube: https://t.co/iiUjKvVZEV
in 2021 i thought there'd be huge anti-ai protests in sf but this was before i learned nothing ever happens
i make things and do research https://t.co/jZh799yNH4 / https://t.co/IdaJwZJCXm
用同样提示词测试了GPT 5.2 ，发现越画越离谱.... 一开始还行，后面开Thinking /Extend Thinking 变小鸡啄米图了。 模型降智太明显了，已用纯净IP了...
Gemini 3画的
RT @seclink: 最近跟着大V小互和宝玉的步伐，我也开通了微博黄V，收获如下： 1. 原先使用的是普通vip，发现没啥用-垃圾广告一堆，发干货，也是0进推荐流。 2. 正好双十二有黄V（svip）的5折（112元年费），发现微博 who to follow和进feed…
找工作、找面试题、改简历、模拟面试。关注： 创业（冷启动） ｜ 认知心理学｜智能体 ｜ 强化学习 building：https://t.co/A4YmEz90B8
Awesome game idea: Multitasking! @play date is so cool. I won’t be able to do that, I’m certain.
CPO at https://t.co/BNZzlkTfVp. Founder of https://t.co/hOAmca8qLm and https://t.co/dRwgbZCSOw. Coffee-making, parenting, building, exploring: RU → CN → NZ → CL → UK → NZ → PL → UK?
用 Notion、印象笔记这类笔记应用时，数据都存在服务商那里，总担心隐私问题或服务停止，而且很多 Electron 应用确实挺占内存的。 无独有偶，在 GitHub 上发现 QOwnNotes 这款开源的桌面笔记应用，它用 C++ 编写，资源占用极低，还能与 Nextcloud/ownCloud 完美配合！ 笔记以纯文本 Markdown 文件形式存储在本地，可以通过 Nextcloud、ownCloud 甚至 Dropbox、Syncthing 等任何同步工具实现多设备同步，数据完全掌握在我们自己手中。 GitHub：https://t.co/oJZEx3ycRy 主要功能： - 原生 C++ 开发，资源占用远低于 Electron 应用； - 支持多个笔记文件夹和层级标签管理； - Markdown 语法高亮和实时预览； - 与 Nextcloud/ownCloud 深度集成，支持版本历史和回收站； - 强大的脚本系统，可安装在线脚本库扩展功能； - 支持笔记加密（AES-256 或自定义加密方式）； - 完全可定制的界面布局和快捷键； - 支持 60 多种语言界面。 支持 Windows、macOS、Linux 系统，可通过各平台包管理器或官网下载安装，适合重视数据自主权和隐私的笔记朋友。
💡 挖掘开源的价值 🧑🏻💻 坚持分享 GitHub 上高质量、有趣、实用的教程、AI工具、前沿 AI 技术 🧐 A list cool, interesting projects of GitHub. ✏️ 公众号：GitHubDaily
