Understand this story
On October 27, 2026, Hi3D open-sourced the original 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 may be used commercially. According to QbitAI, the model is based on the Sparc3D architecture, and its training data consists of about 2 million filtered 3D assets, four times the 500,000 setting in the Sparc3D paper; the technical report shows that its multi-view fidelity and detail richness are 0.75 and 0.841, respectively, with a slice success rate of 90%. The Hi3D Agent launched the same day uses the Hi3D professional 3D model as its base and links intent understanding, generation, modification, and delivery; the latest V3.0 model is said to be commercially usable with 20483 precision. Rohan Paul's report adds that the model receives an image and a coarse mesh generated by another model, refines it in three passes at three resolution levels of 512, 1024, and 1536, and uses sparse voxels and a self-pruning decoder; among 8 compared models, its multi-view fidelity of 0.75 and detail richness of 0.841 are both the highest, and in 562 side-by-side ratings by 13 professional 3D practitioners, 83.5% chose it; the model outputs only shape without color or texture, requires an NVIDIA GPU, and the free commercial-use ceiling is 200,000 monthly active users or $1 million in monthly revenue.
AI-generated from public reports
Latest development · Report
Hi3D Open-Sources the Hi3D v1.0 Image-to-3D ModelDevelopments
1 confirmed developments
- Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 27
Rohan Paul
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.
QbitAI
Hi3D open-sources the commercially usable 3D model V1.0 and launches a 3D creation Agent
Hi3D has open-sourced the V1.0 high-resolution geometry refinement model, now available on GitHub and Hugging Face and commercially usable; the model is based on the Sparc3D architecture, with training data of about 2 million filtered 3D assets, 4 times the 500,000 setting in the Sparc3D paper. According to its technical report, V1.0 achieves multi-view fidelity and detail richness of 0.75 and 0.841 respectively, with a slicing success rate of 90%. The simultaneously launched Hi3D Agent is built on Hi3D's professional 3D models as its foundation, connecting intent understanding, generation, modification, and delivery; the latest V3.0 model is claimed to offer commercially usable 2048³ precision.
Heat trend for this story
- Current
- 11
- Period peak
- 12 Oct 28 13:00
- 24-hour change
- —
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.