Add pipeline tag image-to-3d

This PR adds the `pipeline_tag: image-to-3d` metadata to improve searchability of the model on the Hugging Face Hub.

README.md

@@ -1,8 +1,8 @@
 ---
 license: mit
+pipeline_tag: image-to-3d
 ---
 
-
 # Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
 
 <div align="center">
@@ -27,7 +27,7 @@ license: mit
 
 ## 📝 Abstract
 
-Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges. We introduce <strong class="has-text-weight-bold">Direct3D‑S2</strong>, a scalable 3D generation framework based on sparse volumes that achieves superior output quality with dramatically reduced training costs. Our key innovation is the <strong class="has-text-weight-bold">Spatial Sparse Attention (SSA)</strong> mechanism, which greatly enhances the efficiency of Diffusion Transformer (DiT) computations on sparse volumetric data. SSA allows the model to effectively process large token sets within sparse volumes, substantially reducing computational overhead and achieving a <em>3.9&times;</em> speedup in the forward pass and a <em>9.6&times;</em> speedup in the backward pass. Our framework also includes a variational autoencoder (VAE) that maintains a consistent sparse volumetric format across input, latent, and output stages. Compared to previous methods with heterogeneous representations in 3D VAE, this unified design significantly improves training efficiency and stability. Our model is trained on public available datasets, and experiments demonstrate that <strong class="has-text-weight-bold">Direct3D‑S2</strong> not only surpasses state-of-the-art methods in generation quality and efficiency, but also enables <strong class="has-text-weight-bold">training at 1024<sup>3</sup>  resolution with just 8 GPUs</strong>, a task typically requiring at least 32 GPUs for volumetric representations at 256<sup>3</sup> resolution, thus making gigascale 3D generation both practical and accessible.
+Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges. We introduce **Direct3D‑S2**, a scalable 3D generation framework based on sparse volumes that achieves superior output quality with dramatically reduced training costs. Our key innovation is the **Spatial Sparse Attention (SSA)** mechanism, which greatly enhances the efficiency of Diffusion Transformer (DiT) computations on sparse volumetric data. SSA allows the model to effectively process large token sets within sparse volumes, substantially reducing computational overhead and achieving a *3.9×* speedup in the forward pass and a *9.6×* speedup in the backward pass. Our framework also includes a variational autoencoder (VAE) that maintains a consistent sparse volumetric format across input, latent, and output stages. Compared to previous methods with heterogeneous representations in 3D VAE, this unified design significantly improves training efficiency and stability. Our model is trained on public available datasets, and experiments demonstrate that **Direct3D‑S2** not only surpasses state-of-the-art methods in generation quality and efficiency, but also enables **training at 1024<sup>3</sup> resolution with just 8 GPUs**, a task typically requiring at least 32 GPUs for volumetric representations at 256<sup>3</sup> resolution, thus making gigascale 3D generation both practical and accessible.
 
 ## 🌟 Highlight
 
@@ -39,7 +39,15 @@ Generating high-resolution 3D shapes using volumetric representations such as Si
 
 ### Installation
 
-```sh
+- Install `pytorch >= 2.1.0` and `torchvision` first. You can refer to the [official installation guide](https://pytorch.org/get-started/locally/) for more details.
+
+```bash
+python -m pip install torch torchvision
+```
+
+- Install dependencies:
+
+```bash
 git clone https://github.com/DreamTechAI/Direct3D-S2.git
 
 cd Direct3D-S2
@@ -100,4 +108,4 @@ If you find our work useful, please consider citing our paper:
   journal={arXiv preprint arXiv:2505.17412},
   year={2025}
 }
-```
+```