Hi3D Open-Sources the Hi3D v1.0 Image-to-3D Model
Hi3D has open-sourced the former Sparc3D under the name Hi3D v1.0. This is an image-to-3D model, and its code and weights have been released on GitHub and Hugging Face and can be used commercially. The model takes an image and a coarse mesh generated by another model, refines it in three passes at three resolution levels of 512, 1024, and 1536, uses sparse voxels and a self-pruning decoder, and has expanded its training data from 500K to about 2M 3D assets. Among 8 compared models, its multi-view fidelity of 0.75 and detail richness of 0.841 are both the highest, its 3D print slicing success rate is 90%, and in 562 side-by-side ratings by 13 professional 3D experts, 83.5% chose it; the model outputs only shape without color or texture, requires an NVIDIA GPU, and is free for commercial use up to 200,000 monthly active users or $1 million in monthly revenue.
Why read this
AI score 52
The original text provides comparison data on multi-view fidelity, detail richness, and print slicing success rate, which can be used to assess the current level of open-source image-to-3D models.
Topics
View original posthttps://t.co/FlZfsBfs0T
View original
https://t.co/FlZfsBfs0T
Body
This is so good for open 3D generation. last year’s cutting-edge technology, open-sourced this year
@Hi3D_AI has open-sourced Hi3D v1.0 (formerly Sparc3D), an image-to-3D model that holds together from every angle and already ran in Hi3D’s live product before release.
> Anyone can run it privately on their own servers, connect it to their internal systems, and build tools and apps for their industry on top of it. > Code and weights are on GitHub and Hugging Face, free to use including commercially,
Most image-to-3D models get judged by how the front looks, so the back, the bottom and thin parts like wings, horns and handles often come out blobby, broken or missing.
Hi3D v1.0 takes the image plus a rough draft shape (a “coarse mesh” from another model) and sharpens it in 3 passes, at 512, 1024 and 1536 resolution.
Resolution here means the space around the object is cut into tiny cubes called voxels, basically 3D pixels, and 1536 means 1536 cubes along each side.
That full grid would hold over 3.6B cubes, so the model works sparse, only touching cubes near the surface and skipping empty air and the solid inside.
In each pass, a “self-pruning” decoder rebuilds the surface at 8x finer scale and drops cubes that turn out empty.
Training data grew from 500K to about 2M curated 3D assets.
Against 8 other image-to-3D models, including TRELLIS.2 and Hunyuan3D-2.1, it scored best on multi-view fidelity (0.75), which checks the shape stays consistent and unbroken from 6 camera angles, and detail richness (0.841), which grades fine surface relief and small parts.
It also kept a 90% slicing success rate, the share of models a 3D printer’s software could cut into print layers, versus 7% for Pixal3D, the only other model at 1536, and 17% for TRELLIS.2.
In 562 side-by-side ratings by 13 people with professional 3D experience, Hi3D v1.0 was picked 83.5% of the time.
It outputs shape only (no colors or textures), needs an NVIDIA GPU, and the code and weights are free for commercial use up to 200K monthly users or $1M monthly revenue.
And Hi3D 1.0 Is Now Open Source
https://t.co/AaRHAfa3Bu