IDOL brings image-to-3D Gaussian splatting to Apache
Sperid Labs releases IDOL, an open model that turns images into 3D Gaussian-splat representations under a permissive license.

Sperid Labs has published IDOL, a model that reconstructs 3D scenes from imagery using Gaussian splatting, now available on Hugging Face under the permissive Apache-2.0 license.
Gaussian splatting has become one of the most active areas in 3D graphics and vision, offering a way to represent scenes as collections of 3D Gaussians that can be rendered quickly and with high fidelity. IDOL applies that approach to the image-to-3D problem, taking visual input and producing a splat-based 3D representation.
Why it matters
Open releases in the 3D space remain comparatively rare next to the flood of text and image models, so a permissively licensed entry carries weight for researchers and builders working on reconstruction and content creation.
- Primary modality: text-to-3D, with an image-to-3D workflow
- License: Apache-2.0, allowing commercial use and modification
- Hosted on Hugging Face for direct access
Sperid Labs has not published detailed benchmarks or parameter counts alongside this initial release, so independent evaluation will be the real test. For teams experimenting with 3D asset generation, IDOL offers another open foundation to build and compare against.
Sources
- Visit
speridlabs/idol
Hugging Face
More in Text → 3D
All Text → 3D →Tencent's HY-WorldPlay Creates 3D Scenes from One Image
The new model from Tencent's Hunyuan team generates dynamic video and reconstructs 3D environments using a single static picture.

Tencent's Voyager Model Turns Images into 3D Worlds
The new model from Tencent AI Lab generates temporally and spatially consistent video sequences from a single image, enabling virtual exploration of static scenes.
0 comments
No comments yet. Be the first to weigh in.