---
language:
- en
license: other
license_name: autodesk-non-commercial-3d-generative-v1.0
tags:
- wala
- mult-iview-to-3d
pipeline_tag: image-to-3d
---

# Model Card for WaLa-RGB4-1B

This model is part of the Wavelet Latent Diffusion (WaLa) paper, capable of generating high-quality 3D shapes from four-view RGB inputs with detailed geometry and complex structures.

## Model Details

### Model Description

WaLa-RGB4-1B is a large-scale 3D generative model trained on a massive dataset of over 10 million publicly-available 3D shapes. It can efficiently generate a wide range of high-quality 3D shapes from four-view RGB image inputs in just 2.5 seconds. The model uses a wavelet-based compact latent encoding and a billion-parameter architecture to achieve superior performance in terms of geometric detail and structural plausibility.

- **Developed by:** Aditya Sanghi, Aliasghar Khani, Chinthala Pradyumna Reddy, Arianna Rampini, Derek Cheung, Kamal Rahimi Malekshan, Kanika Madan, Hooman Shayani
- **Model type:** 3D Generative Model
- **License:** Autodesk Non-Commercial (3D Generative) v1.0

For more information please look at the [Project Page](https://autodeskailab.github.io/WaLaProject) and [the paper](TBD).

### Model Sources

- **Project Page:** [WaLa](https://autodeskailab.github.io/WaLaProject)
- **Repository:** [Github](https://github.com/AutodeskAILab/WaLa)
- **Paper:** [ArXiv](https://arxiv.org/abs/2411.08017)
- **Demo:** [Colab](https://colab.research.google.com/drive/1W5zPXw9xWNpLTlU5rnq7g3jtIA2BX6aC?usp=sharing)

## Uses

### Direct Use

This model is released by Autodesk and intended for academic and research purposes only for the theoretical exploration and demonstration of the WaLa 3D generative framework. Please see [here](https://github.com/AutodeskAILab/WaLa?tab=readme-ov-file#multi-view-to-3d) for inferencing instructions. 

### Out-of-Scope Use

The model should not be used for:

- Commercial purposes 

- Creation of load-bearing physical objects the failure of which could cause property damage or personal injury 

- Any usage not in compliance with the [license](https://huggingface.co/ADSKAILab/WaLa-RGB4-1B/blob/main/LICENSE.md), in particular, the "Acceptable Use" section. 

## Bias, Risks, and Limitations

### Bias

- The model may inherit biases present in the publicly-available training datasets, which could lead to uneven representation of certain object types or styles. 

- The model's performance may degrade for object categories or styles that are underrepresented in the training data. 

### Risks and Limitations

- The quality of the generated 3D output may be impacted by the quality and clarity of the input images.
- The model may occasionally generate implausible shapes, especially when the input images are ambiguous or of low quality. Even theoretically plausible shapes should not be relied upon for real-world structural soundness.

## How to Get Started with the Model

Please refer to the instructions [here](https://github.com/AutodeskAILab/WaLa?tab=readme-ov-file#getting-started)

## Training Details

### Training Data

The model was trained on a dataset of over 10 million 3D shapes aggregated from 19 different publicly-available sub-datasets, including ModelNet, ShapeNet, SMLP, Thingi10K, SMAL, COMA, House3D, ABC, Fusion 360, 3D-FUTURE, BuildingNet, DeformingThings4D, FG3D, Toys4K, ABO, Infinigen, Objaverse, and two subsets of ObjaverseXL (Thingiverse and GitHub).

### Training Procedure

#### Preprocessing

Each 3D shape in the dataset was converted into a truncated signed distance function (TSDF) with a resolution of 256³. The TSDF was then decomposed using a discrete wavelet transform to create the wavelet-tree representation used by the model. For multi-view conditioning, four views were selected from pre-selected viewpoints to ensure comprehensive coverage of the entire object.

#### Training Hyperparameters

- **Training regime:** Please refer to the paper.

#### Speeds, Sizes, Times

- The model contains approximately 956 million parameters.
- The model can generate shapes within 2-4 seconds.

## Evaluation

### Testing Data, Factors & Metrics

#### Testing Data

The model was evaluated on the Google Scanned Objects (GSO) dataset and a validation set from the training data (MAS validation data).

#### Factors

The evaluation considered various factors such as the quality of generated shapes, the ability to capture fine details and complex structures, and the model's performance across different object categories.

#### Metrics

The model was evaluated using the following metrics:
- Intersection over Union (IoU)
- Light Field Distance (LFD)
- Chamfer Distance (CD)

### Results

The multi-view (RGB4) to 3D model achieved the following results on the GSO dataset:
- LFD: 1260.64
- IoU: 0.8500
- CD: 0.00182

On the MAS validation dataset:
- LFD: 1540.22
- IoU: 0.8175
- CD: 0.00208

## Technical Specifications

### Model Architecture and Objective

The model uses a U-ViT architecture with modifications. It employs a wavelet-based compact latent encoding to effectively capture both coarse and fine details of 3D shapes from multi-view RGB inputs. Each selected view is processed individually through the DINO v2 encoder, generating a sequence of latent vectors for each view. The latent vectors from all views are concatenated to form the final conditional latent vectors.

### Compute Infrastructure

#### Hardware

The model was trained on NVIDIA H100 GPUs.

## Citation
```
@misc{sanghi2024waveletlatentdiffusionwala,
      title={Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings}, 
      author={Aditya Sanghi and Aliasghar Khani and Pradyumna Reddy and Arianna Rampini and Derek Cheung and Kamal Rahimi Malekshan and Kanika Madan and Hooman Shayani},
      year={2024},
      eprint={2411.08017},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2411.08017}, 
}
```