Update README.md

README.md

@@ -4,6 +4,8 @@ license_name: stabilityai-ai-community
 license_link: LICENSE.md
 tags:
 - image-to-3d
+datasets:
+  - allenai/objaverse
 inference: false
 pipeline_tag: image-to-3d
 extra_gated_prompt: >-
@@ -24,31 +26,39 @@ extra_gated_fields:
 ---
 
 
-# SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images
+# SPAR3D: Stable Point Aware 3D 
 ![](spar3d.gif)
+**Stable Point Aware 3D (SPAR3D)** is a large reconstruction model based on [SF3D](https://huggingface.co/stabilityai/stable-fast-3d), that introduces the ability to make real-time edits and generate a textured UV-unwrapped 3D mesh asset from a single image in less than a second. By introducing a first-of-its-kind two-stage architecture, SPAR3D combines the benefits of a fast point cloud diffusion model with regressive mesh predictions to enable unparalleled control over 3D object generation.
 
-Please note: For individuals or organizations generating annual revenue of US $1,000,000 (or local currency equivalent) or more, regardless of the source of that revenue, you must obtain an enterprise commercial license directly from Stability AI before commercially using SF3D or any derivative work of SF3D or its outputs, such as "fine tune" models. You may submit a request for an Enterprise License at https://stability.ai/enterprise. Please refer to Stability AI's Community License, available at https://stability.ai/license, for more information.
+
+Please note: For individuals or organizations generating annual revenue of US $1,000,000 (or local currency equivalent) or more, regardless of the source of that revenue, you must obtain an enterprise commercial license directly from Stability AI before commercially using SPAR3D, any derivative work of SPAR3D (such as a “fine tune” model), or their outputs. You may submit a request for an Enterprise License at https://stability.ai/enterprise. Please refer to Stability AI's Community License, available at https://stability.ai/license, for more information.
 
 
 ### Model Description
 
 * **Developed by**: [Stability AI](https://stability.ai/)
 * **Model type**: Transformer image-to-3D model
-* **Model details**: This model is based on [Stable Fast 3D](https://github.com/Stability-AI/stable-fast-3d) but improves upon the backside of the mesh by conditioning on a point cloud. This point cloud can be generated from an image using our included point cloud denoising model. This point cloud can even be edited easily in external tools or our included gradio demo. With that missing backside details can be fixed. We further improve the prediction quality of materials using novel contributions. We achieve all of this while still maintaining the fast inference speeds.
+* **Model details**: This model is trained to create a 3D model from a single image in under one second. The asset is UV-unwrapped and textured. We also perform a delighting step, enabling easier asset usage in downstream applications such as game engines or rendering work. The model also predicts per-object material parameters (roughness, metallic), enhancing reflective behaviors during rendering. The model expects an input size of 512x512 pixels. We achieve improved backside modelling using a fast point diffusion model, which acts as a conditioning.
+Please check our [tech report]() and [video summary](https://youtu.be/mlO3Nc3Nsng) for details.
 
 
 ### License
 
-- **Community License:** Free for research, non-commercial, and commercial use by organizations and individuals generating annual revenue of US $1,000,000 (or local currency equivalent) or less, regardless of the source of that revenue. If your annual revenue exceeds US $1M, any commercial use of this model or derivative works thereof requires obtaining an Enterprise License directly from Stability AI. You may submit a request for an Enterprise License at https://stability.ai/enterprise. Please refer to Stability AI's Community License, available at https://stability.ai/license, for more information.
+- **Community License:** Free for research, non-commercial, and commercial use by organizations and individuals generating annual revenue of US $1,000,000 (or local currency equivalent) or more, regardless of the source of that revenue. If your annual revenue exceeds US $1M, any commercial use of this model or derivative works thereof requires obtaining an Enterprise License directly from Stability AI. You may submit a request for an Enterprise License at https://stability.ai/enterprise. Please refer to Stability AI's Community License, available at https://stability.ai/license, for more information.
 
 
 ### Model Sources
 
-* **Repository**: https://github.com/Stability-AI/stable-point-aware-3d
-* **Tech report**: https://arxiv.org/abs/2408.00653
-* **Video summary**: https://youtu.be/uT96UCBSBko
-* **Project page**: https://stable-point-aware-3d.github.io
-* **arXiv page**: https://arxiv.org/abs/2408.00653
+* **Repository**: [https://github.com/Stability-AI/stable-point-aware-3d](https://github.com/Stability-AI/stable-point-aware-3d)
+* **Tech report**: soon
+* **Video summary**: [https://youtu.be/mlO3Nc3Nsng](https://youtu.be/mlO3Nc3Nsng)
+* **Project page**: [https://spar3d.github.io](https://spar3d.github.io)
+* **arXiv page**: soon
+
+
+### Training Dataset
+
+We use renders from the [Objaverse](https://objaverse.allenai.org/) dataset, available under the Open Data Commons Attribution License. We utilize our enhanced rendering method, which more closely replicates the distribution of images found in the real world, significantly improving our model's ability to generalize. We filter objects based on the review of licenses and curate a subset suitable for our training needs.
 
 
 ## Usage
@@ -73,7 +83,7 @@ The model was not trained to be factual or true representations of people or eve
 
 ## Safety
 
-As part of our safety-by-design and responsible AI deployment approach, we implement safety measures throughout the development of our models, from the time we begin pre-training a model to the ongoing development, fine-tuning, and deployment of each model. We have implemented a number of safety mitigations that are intended to reduce the risk of severe harms. However, we recommend that developers conduct their own testing and apply additional mitigations based on their specific use cases.  
+As part of our safety-by-design and responsible AI deployment approach, we implement safety measures throughout the development of our models, from the time we begin pre-training a model to the ongoing development, fine-tuning, and deployment of each model. We have implemented a number of safety mitigations that are intended to reduce the risk of severe harms. However, it is the responsibility of developers to conduct their own testing and apply additional mitigations based on their specific use cases.  
 For more about our approach to Safety, please visit our [Safety page](https://stability.ai/safety).