Update README.md

README.md

@@ -9,46 +9,80 @@ language:
 # Model Card for PartPacker
 
 ## Description
-PartPacker takes a single input image and generates a 3D shape with an arbitrary number of complete parts. 
+PartPacker is a three-dimensional (3D) generation model that is able to generate part-level 3D objects from single-view images.
 We introduce a dual volume packing strategy that organizes all parts into two complementary volumes, allowing for the creation of complete and interleaved parts that assemble into the final object. 
 This model is ready for non-commercial use.
 
 ## License/Terms of Use
 [NVIDIA Non-Commercial License](https://huggingface.co/nvidia/PartPacker/blob/main/LICENSE)
 
+
+## Deployment Geography
+Global
+
+## Use Case
+PartPacker takes a single input image and generates a 3D shape with an arbitrary number of complete parts. Each part can be separated and edited independently to facilitate downstream tasks such as editing and animation.  
+It's intended to be used by researchers and academics to develop new 3D generation methods.
+
+## Release Date
+* Github: 06/04/2025 via [https://github.com/NVlabs/PartPacker](https://github.com/NVlabs/PartPacker)  
+* Huggingface: 06/04/2025 via [https://huggingface.co/NVlabs/PartPacker](https://huggingface.co/NVlabs/PartPacker)  
+
+## Reference(s)
+[Code](https://github.com/NVlabs/PartPacker)  
+[Paper](https://arxiv.org/abs/TODO)  
+
 ## Model Architecture
-**Architecture Type:** Transformer
+**Architecture Type:** Transformer    
+**Network Architecture:** Diffusion Transformer (DiT)    
+
 
 ## Input
 **Input Type(s):** Image  
-**Input Format(s):** RGB Image  
-**Input Parameters:** 2D Image  
-**Other Properties Related to Input:** Condition for the model.  
+**Input Format(s):** Red, Green, Blue (RGB)  
+**Input Parameters:** Two-dimensional (2D) image  
+**Other Properties Related to Input:** Resolution will be resized to $518 \times 518$.
 
 ## Output
-**Output Type(s):** Mesh  
-**Output Format:** GLB  
-**Output Parameters:** 3D Mesh  
-**Other Properties Related to Output:** Generated 3D shape with parts.  
+**Output Type(s):** Triangle Mesh  
+**Output Format:** GL Transmission Format Binary (GLB)  
+**Output Parameters:** Three-dimensional (3D) triangle mesh    
+**Other Properties Related to Output:** Extracted at a resolution up to $512^3$; without texture.  
 
-## Supported Hardware Microarchitecture Compatibility
+Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
+
+## Software Integration
+
+### Runtime Engine(s)
+* PyTorch
+
+### Supported Hardware Microarchitecture Compatibility
 * NVIDIA Ampere
 * NVIDIA Hopper
 
-## Supported Operating System(s)
+### Preferred Operating System(s)
 * Linux
 
 ## Model Version(s)
 v1.0
 
-## Training Dataset
-[Objaverse-XL](https://objaverse.allenai.org/)  
-**Properties:** We use about 250k mesh data, which is a subset from the Objaverse-XL with part-level annotations.  
-**Dataset License(s):** The use of the dataset as a whole is licensed under the ODC-By v1.0 license.  
+## Training, Testing, and Evaluation Datasets
+
+We perform training, testing, and evaluation on the Objaverse-XL dataset.
+For the VAE model, we use the first 253K meshes for training and the rest 1K meshes for validation.
+For the Flow model, we use all 254K meshes for training.
+### Objaverse-XL
+
+**Link**: https://objaverse.allenai.org/  
+**Data Collection Method**: Hybrid: Automatic, Synthetic  
+**Labeling Method by dataset**: N/A (no labels)  
+**Properties:** We use about 254k mesh data, which is a subset from the Objaverse-XL filtered by the number of parts.  
 
 
 ## Inference
-Pytorch
+
+**Acceleration Engine**: PyTorch  
+**Test Hardware**: NVIDIA A100 (1 GPU configuration)
 
 
 ## Ethical Considerations