deepopen-3d-webs
You supply one reference image and a prompt, and the system generates scene results along a camera trajectory that you can preview, replay, and trace.
deepopen-3d-webs launched on 26 October 2026. It ranked #31 on Daily Launch on 31 October 2026 with a Launch Score of 49, from 972 stars in 4 days on GitHub. It was new in the ranking that day.
What is Deepopen 3d Webs?
You supply one reference image and a prompt, and the system generates scene results along a camera trajectory that you can preview, replay, and trace. The official 3D demo assets play color/depth animations and Gaussian point clouds directly in the browser. The web app ships as a Docker image and listens on port 8090 by default.
From its README on GitHub
Deepopen 3d Webs (deepopen-3d-webs) is a repo by deepopen-com on GitHub. It is written in Python.
How to get Deepopen 3d Webs
Get it from its repository on GitHub.
Screenshot of deepopen.com
In its own words
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
From its GitHub repository
Launch timeline
Launch Score, last 7 days
Ranked on one day so far: 49 of 100 on 31 October.