model card: architecture figure + dataset link

README.md

@@ -16,6 +16,7 @@ base_model: stabilityai/stable-video-diffusion-img2vid
 
 [![Project Page](https://img.shields.io/badge/Project-Page-blue)](https://jaibardhan.com/depthworld/)
 [![GitHub](https://img.shields.io/badge/GitHub-depthworld-black)](https://github.com/Jai2500/depthworld)
+[![Dataset](https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-droid__3d__extrinsics-yellow)](https://huggingface.co/datasets/jaibrdhn/droid_3d_extrinsics)
 [![ArXiv](https://img.shields.io/badge/ArXiv-coming_soon-red)](https://jaibardhan.com/depthworld/)
 
 ## TL;DR
@@ -27,6 +28,8 @@ world. RGB and depth are packed side-by-side along width per view and
 modeled by a single Stable Video Diffusion UNet; an optional DPT head
 additionally regresses per-pixel world-frame point maps.
 
+![DepthWorld architecture](architecture.png)
+
 ## Checkpoints
 
 Both are consolidated 90k-step EMA weights (fp32 `.pt` state dicts), trained