openlrm-obj-small-1.1 Open-Source Model - Easily Generate 3D Models from a Single Image

Home

Openlrm Obj Small 1.1

Developed by zxhezexin

OpenLRM is an open-source implementation of the LRM paper for generating 3D models from a single image

3D Vision

Transformers

#Single-image 3D Reconstruction #Tri-plane Decoding #DINOv2 Encoding

Downloads 58

Release Time : 3/4/2024

Model Overview

OpenLRM is a Transformer-based image-to-3D model generation system that predicts tri-plane representations of Neural Radiance Fields (NeRF) from a single input image to generate 3D models.

Model Features

Multi-scale Model Selection

Offers small/base/large model scales to meet different computational resource requirements

Dual-data Training Versions

Provides pure Objaverse-trained version and Objaverse+MVImgNet mixed training version

Efficient 3D Representation

Utilizes tri-plane representation for efficient 3D model generation

DINOv2 Image Encoding

Uses DINOv2 model with registered tokens as image encoder to enhance feature extraction

Model Capabilities

Single-image 3D Reconstruction

Neural Radiance Field Prediction

Tri-plane Representation Generation

Use Cases

3D Content Creation

Rapid 3D Modeling

Quickly generate 3D model prototypes from single product photos

Significantly reduces 3D modeling time

Virtual Scene Construction

Build 3D virtual scenes based on real-world images

Accelerates virtual environment creation process

Educational Research

3D Reconstruction Research

Used for 3D reconstruction algorithm research in computer vision and graphics fields

🚀 Model Card for OpenLRM V1.1

This model card provides detailed information about the OpenLRM V1.1 project, an open - source implementation of the LRM paper, including model details, differences from the original paper, license, and usage considerations.

🚀 Quick Start

This model card is for the OpenLRM project, which is an open - source implementation of the paper LRM. The information contained in this model card corresponds to Version 1.1.

✨ Features

Model Details

Training Data

Property	Details
[openlrm - obj - small - 1.1](https://huggingface.co/zxhezexin/openlrm - obj - small - 1.1)	Objaverse
[openlrm - obj - base - 1.1](https://huggingface.co/zxhezexin/openlrm - obj - base - 1.1)	Objaverse
[openlrm - obj - large - 1.1](https://huggingface.co/zxhezexin/openlrm - obj - large - 1.1)	Objaverse
[openlrm - mix - small - 1.1](https://huggingface.co/zxhezexin/openlrm - mix - small - 1.1)	Objaverse + MVImgNet
[openlrm - mix - base - 1.1](https://huggingface.co/zxhezexin/openlrm - mix - base - 1.1)	Objaverse + MVImgNet
[openlrm - mix - large - 1.1](https://huggingface.co/zxhezexin/openlrm - mix - large - 1.1)	Objaverse + MVImgNet

Model Architecture (version==1.1)

Type	Layers	Feat. Dim	Attn. Heads	Triplane Dim.	Input Res.	Image Encoder	Size
small	12	512	8	32	224	dinov2_vits14_reg	446M
base	12	768	12	48	336	dinov2_vitb14_reg	1.04G
large	16	1024	16	80	448	dinov2_vitb14_reg	1.81G

Training Settings

Type	Rend. Res.	Rend. Patch	Ray Samples
small	192	64	96
base	288	96	96
large	384	128	128

Notable Differences from the Original Paper

We do not use the deferred back - propagation technique in the original paper.
We used random background colors during training.
The image encoder is based on the DINOv2 model with register tokens.
The triplane decoder contains 4 layers in our implementation.

📄 License

The model weights are released under the Creative Commons Attribution - NonCommercial 4.0 International License.
They are provided for research purposes only, and CANNOT be used commercially.

📚 Documentation

Disclaimer

This model is an open - source implementation and is NOT the official release of the original research paper. While it aims to reproduce the original results as faithfully as possible, there may be variations due to model implementation, training data, and other factors.

Ethical Considerations

⚠️ Important Note

This model should be used responsibly and ethically, and should not be used for malicious purposes. Users should be aware of potential biases in the training data. The model should not be used under the circumstances that could lead to harm or unfair treatment of individuals or groups.

Usage Considerations

⚠️ Important Note

The model is provided "as is" without warranty of any kind. Users are responsible for ensuring that their use complies with all relevant laws and regulations. The developers and contributors of this model are not liable for any damages or losses arising from the use of this model.

This model card is subject to updates and modifications. Users are advised to check for the latest version regularly.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご