--- '[object Object]': null language: - en license: other license_name: autodesk-non-commercial-3d-generative-v1.0 license_link: LICENSE.md tags: - make-a-shape - sv-to-3d --- --- # Model Card for Make-A-Shape Single-View to 3D Model This model is part of the Make-A-Shape paper, capable of generating high-quality 3D shapes from single-view images with intricate geometric details, realistic structures, and complex topologies. ## Model Details ### Model Description Make-A-Shape is a novel 3D generative framework trained on an extensive dataset of over 10 million publicly-available 3D shapes. The single-view to 3D model is one of the conditional generation models in this framework. It can efficiently generate a wide range of high-quality 3D shapes from single-view image inputs in just 2 seconds. The model uses a wavelet-tree representation and adaptive training strategy to achieve superior performance in terms of geometric detail and structural plausibility. - **Developed by:** Ka-Hei Hui, Aditya Sanghi, Arianna Rampini, Kamal Rahimi Malekshan, Zhengzhe Liu, Hooman Shayani, Chi-Wing Fu - **Model type:** 3D Generative Model - **License:** Autodesk Non-Commercial (3D Generative) v1.0 For more information please look at the [Project](https://www.research.autodesk.com/publications/generative-ai-make-a-shape/) [Page](https://edward1997104.github.io/make-a-shape/) and [the ICML paper](https://proceedings.mlr.press/v235/hui24a.html). ### Model Sources - **Repository:** [https://github.com/AutodeskAILab/Make-a-Shape](https://github.com/AutodeskAILab/Make-a-Shape) - **Paper:** [Make-A-Shape: a Ten-Million-scale 3D Shape Model](https://proceedings.mlr.press/v235/hui24a.html) - **Demo:** [in progress...] ## Uses ### Direct Use Please look at the instructions [here](https://github.com/AutodeskAILab/Make-a-Shape?tab=readme-ov-file#single-view-to-3d) to test this model for research and acadeic purposes. ### Downstream Use This model could potentially be used in various applications such as: - 3D content creation for gaming and virtual environments - Augmented reality applications - Computer-aided design and prototyping - Architectural visualization ### Out-of-Scope Use The model should not be used for: - Commercial use - Generating 3D shapes of sensitive or copyrighted content without proper authorization - Creating 3D models intended for harmful or malicious purposes ## Bias, Risks, and Limitations - The model may inherit biases present in the training dataset, which could lead to uneven representation of certain object types or styles. - The quality of the generated 3D shape depends on the quality and clarity of the input image. - The model may occasionally generate implausible shapes, especially when the input image is ambiguous or of low quality. - The model's performance may degrade for object categories or styles that are underrepresented in the training data. ### Recommendations Users should be aware of the potential biases and limitations of the model. It's recommended to: - Use high-quality, clear input images for best results - Verify and potentially post-process the generated 3D shapes for critical applications - Be cautious when using the model for object categories that may be underrepresented in the training data - Consider ethical implications and potential biases - DO NOT USE for commercial or public-facing applications ## How to Get Started with the Model [More Information Needed] ## Training Details ### Training Data The model was trained on a dataset of over 10 million 3D shapes aggregated from 18 different publicly-available sub-datasets, including ModelNet, ShapeNet, SMPL, 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. #### Training Hyperparameters - **Training regime:** Please look at the paper. #### Speeds, Sizes, Times - The model was trained on 48 × A10G GPUs for about 20 days, amounting to around 23,000 GPU hours. - The model can generate shapes within two seconds for most conditions. ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data The model was evaluated on a test set consisting of 2% of the shapes from each sub-dataset in the training data, as well as on the entire Google Scanned Objects (GSO) dataset, which was not part of the training 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 single-view to 3D model achieved the following results on the "Our Val" dataset: - LFD: 4071.33 - IoU: 0.4285 - CD: 0.01851 On the GSO dataset: - LFD: 3406.61 - IoU: 0.5004 - CD: 0.01748 ## Technical Specifications ### Model Architecture and Objective The model uses a U-ViT architecture with learnable skip-connections between the convolution and deconvolution blocks. It employs a wavelet-tree representation and a subband adaptive training strategy to effectively capture both coarse and fine details of 3D shapes. ### Compute Infrastructure #### Hardware The model was trained on 48 × A10G GPUs. ## Citation **BibTeX:** @InProceedings{pmlr-v235-hui24a, title = {Make-A-Shape: a Ten-Million-scale 3{D} Shape Model}, author = {Hui, Ka-Hei and Sanghi, Aditya and Rampini, Arianna and Rahimi Malekshan, Kamal and Liu, Zhengzhe and Shayani, Hooman and Fu, Chi-Wing}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {20660--20681}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/hui24a/hui24a.pdf}, url = {https://proceedings.mlr.press/v235/hui24a.html}, abstract = {The progression in large-scale 3D generative models has been impeded by significant resource requirements for training and challenges like inefficient representations. This paper introduces Make-A-Shape, a novel 3D generative model trained on a vast scale, using 10 million publicly-available shapes. We first innovate the wavelet-tree representation to encode high-resolution SDF shapes with minimal loss, leveraging our newly-proposed subband coefficient filtering scheme. We then design a subband coefficient packing scheme to facilitate diffusion-based generation and a subband adaptive training strategy for effective training on the large-scale dataset. Our generative framework is versatile, capable of conditioning on various input modalities such as images, point clouds, and voxels, enabling a variety of downstream applications, e.g., unconditional generation, completion, and conditional generation. Our approach clearly surpasses the existing baselines in delivering high-quality results and can efficiently generate shapes within two seconds for most conditions.} } **APA:** Hui, K. H., Sanghi, A., Rampini, A., Malekshan, K. R., Liu, Z., Shayani, H., & Fu, C. W. (2024). Make-A-Shape: a Ten-Million-scale 3D Shape Model. arXiv preprint arXiv:2401.08504. ## Model Card Contact [hooman.shayani@autodesk.com]