⬢github Python · 1.1K ★ +259 since we first saw it · pushed 8 d ago
deepopen-com/deepopen-3d-webs
Image-driven 3D scene generation system. Users provide a reference image and prompt words, and the system generates previewable, replayable, and traceable scene results according to the camera trajectory; official 3D demonstration assets allow direct viewing of color/depth animations and Gaussian point clouds in the browser 图像驱动的三维场景生成系统
DeepOpen-3d-webs (光域造景) is a Python web app that turns a single reference image plus a text prompt into explorable 3D scenes. It generates preview stills, color/depth animations, and Gaussian-splatting point clouds along camera trajectories, viewable in the browser, with PLY export, task history, and a Docker-based web UI (default port 8090).
Why now: It appeared among the most-starred new repositories, gaining over 1,100 stars within roughly a day of release.
Who it is for: Designers, educators, and creators who want image-to-3D scene generation and browser-based Gaussian point cloud previews without stitching together separate tools.
3dgaussian-filtergaussian-splatting
Stars over our 453 snapshots: 863 to 1.1K, since 4 d ago.
Where people talked about it
- ⬢github new repos, most starred 11 min ago
- ⬢github new repos, most starred 1 d ago
- ⬢github new repos, most starred 2 d ago
- ⬢github new repos, most starred 3 d ago
- ⬢github new repos, most starred 4 d ago
API: https://socialmediatrends-api.osmike.com/v1/repos/deepopen-com/deepopen-3d-webs