#2525th of 56 in Image and videoFor image, video and design, 3d, science, health and research, robotics
infinigen
Procedural 3D scene generator on Blender with ground-truth renders
- Stars
- 7.4k
- License
- BSD-3-Clause
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
6,884 on 21 Apr 20267,414 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Infinigen generates 3D scenes procedurally in Python on top of Blender, covering outdoor nature, indoor rooms and articulated simulation assets. It renders images with ground-truth annotations such as depth, surface normals and instance segmentation. Scenes can be exported to formats like OBJ and OpenUSD, or to physics simulators.
Who it is for: Computer vision and robotics researchers needing synthetic 3D scenes with labels
Strengths
- Renders depth, surface normals and instance segmentation alongside RGB images
- Covers nature, indoor scenes and articulated sim assets in one codebase
- Exports to OBJ, OpenUSD and physics simulators
- Scenes are generated procedurally, so output varies by seed instead of fixed assets
Weaknesses
- Install and usage steps are split across several version branches and docs pages
- Not a diffusion-model tool; it needs a Blender-based setup and config tuning
- Contributor tutorials and guidelines are marked as coming soon
- Pre-generated data repository is announced but not yet available
What it needs
- Docker
- Needs Blender
Quick answers
Is infinigen open source?
Yes. Its code is on GitHub under the BSD-3-Clause license.
Can you run infinigen with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Image and video
See all 56| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 92 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 86 out of 100 |
| #4 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |
| #5 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 85 out of 100 |