The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper Structured 3D Latents for Scalable and Versatile 3D Generation.
ABot-Recon-Axera is an open-weight model for image to 3d from AXERA, released under Creative Commons Attribution-NonCommercial 4.0. Its published files total 1.4 GB.
ABot-Recon(流式前馈三维重建:视频 → 相机位姿 + 世界坐标点云 + 置信度)编译到 Axera AX650N NPU 的模型文件。 模型与算法来自原作者:amap-cvlab/ABot-Recon(主页 ),本仓库只做 Axera NPU 的格式转换。 代码与使用说明:https://github.com/AXERA-TECH/ABot-Recon-Axera 三个 axmodel 由 pulsar2 编译,芯片 AX650N,支持 AXCL PCIe 卡和 AX650 片上两种运行方式。 打开…
Parameters—
Context—
Weights26.4 MB
Licensecc-by-nc-4.0
AccessOpen weights
Monthly Downloads—
Model Card
ABot-Recon(流式前馈三维重建:视频 → 相机位姿 + 世界坐标点云 + 置信度)编译到 Axera AX650N NPU 的模型文件。 模型与算法来自原作者:amap-cvlab/ABot-Recon(主页 ),本仓库只做 Axera NPU 的格式转换。 代码与使用说明:https://github.com/AXERA-TECH/ABot-Recon-Axera 三个 axmodel 由 pulsar2 编译,芯片 AX650N,支持 AXCL PCIe 卡和 AX650 片上两种运行方式。 打开 http://:8011。Python 调用: 片上运行需要板子 CMM 预留 ≥ 6 GB。 这些权重转换自 ABot-Recon 发布的权重,后者派生自 Pi3;再分发须保留对 Pi3 与 ABot-Recon 的署名与 CC BY-NC 4.0 条款。商业使用需另行获得书面授权。 - presentvalid 封顶 8(应为 11),长序列有轻微漂移。
Excerpt from the card by AXERA, licensed cc-by-nc-4.0.
Identity and Version
- Repository
- AXERA-TECH/ABot-Recon-Axera
- Publisher
- AXERA
- Task
- Image to 3d
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- fbe73fc5686c6c0ed2af5255272cf3ebf248da58
- First published
- 2026-09-14
- Last updated
- 2026-09-19
Files and Weights
14 files, 1.4 GB in total. The weights are 1 file totalling 26.4 MB in safetensors.
Weights1 file · 26.4 MB
Configuration2 files · 400 B
Documentation7 files · 23.9 KB
Other3 files · 1.4 GB
Repository1 file · 1.7 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| host_pose_head/pose_head.safetensors | Weights | 26.4 MB | f6805c677f38 |
| config.json | Configuration | — | |
| host_pose_head/pose_head_config.json | Configuration | 400 B | — |
| LICENSE | Documentation | 11.4 KB | — |
| MODEL_LICENSE.md | Documentation | 810 B | — |
| MODEL_USAGE_GUIDELINES.md | Documentation | 2.7 KB | — |
| MODEL_USAGE_GUIDELINES_ZH.md | Documentation | 2.1 KB | — |
| NOTICE | Documentation | 1.5 KB | — |
| README.md | Documentation | 3.6 KB | — |
| THIRD_PARTY_NOTICES.md | Documentation | 1.8 KB | — |
| decoder_step_kitti02.axmodel | Other | 818.6 MB | 14e233e0637a |
| encoder_kitti02.axmodel | Other | 347.8 MB | 4630d92135d7 |
| heads_kitti02.axmodel | Other | 227.1 MB | a7e1ca075a63 |
| .gitattributes | Repository | 1.7 KB | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 26.4 MB
Download from AXERA
Released by AXERA through its official repository on Hugging Face. Read the license.
Built From
- Derived from acvlab/ABot-Recon
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 26.4 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About ABot-Recon-Axera
Can I use ABot-Recon-Axera commercially?
Not without separate permission. ABot-Recon-Axera is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
Similar Models
TRELLIS.2 is a state-of-the-art large 3D generative model designed for high-fidelity image-to-3D generation. It leverages a novel "field-free" sparse voxel structure termed O-Voxel and a large-scale flow-matching transformer (4 Billion parameters). Unlike previous methods that rely on iso-surface fields (e.g., SDF, Flexicubes) which struggle with open surfaces or non-manifold geometry, TRELLIS can reconstruct and generate arbitrary 3D assets with complex topologies, sharp features, and full Physical-Based Rendering (PBR) materials—including transparency/translucency. - The CUDA Toolkit is needed to compile certain packages. Recommended version is 12.4. - Conda is recommended for managing…
Matchanu 1.5 is PyGrassReal's generative 3D asset engine capable of synthesizing production-ready watertight 3D meshes (STL, OBJ, PLY) and real-time 3D Gaussian Splats from text descriptions or single 2D concept images. Designed for Industrial Prototyping (3D Printing), Game & AR/VR Assets, and Architectural Elements, Matchanu 1.5 generates clean topology, UV unwrappings, and volume-accurate meshes without the point cloud artifacts common to open-source prototypes. 1. Prompt & Image-to-3D Mesh: - Converts single-view product photos or text prompts into clean, manifold 3D meshes ready for Blender, Rhino, Maya, or Unreal Engine. 2. 3D Printing Ready (Watertight Topology): - Automatically…