
Pixal3D is TencentARC’s image-to-3D research project, with inference, training and data-preparation code described in its public repository. The maintainers list multi-view inference as a September 2026 addition. Read the original announcement and project details.
Why it matters
The workflow is relevant to creators exploring how an image can guide 3D asset generation, but generated geometry and textures still need inspection and editing for use in a game. It is a research project spotlight, not a new November release.
What to know
Review repository and model-weight licenses separately, along with dependencies and GPU memory requirements. We have not installed this project or tested whether it fits a 12 GB graphics card.
EXPLORE THE SOURCE
Projects in this story
GitHub repositories
- TencentARC/Pixal3D ↗View project details
Reported from linked primary sources. No model or product was independently tested.



