Add current teaser and method figures

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/teaser.png filter=lfs diff=lfs merge=lfs -text
+assets/method_overview.png filter=lfs diff=lfs merge=lfs -text
+assets/hcvae.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -26,6 +26,29 @@ The inference code and installation instructions are maintained at
 inputs are hosted at
 [datasets/hongchi/Fire3D](https://huggingface.co/datasets/hongchi/Fire3D).
 
+## Overview
+
+![Fire3D reconstructs compositional, simulation-ready 3D scenes from RGB-D observations.](assets/teaser.png)
+
+**Teaser.** Fire3D reconstructs a compositional 3D scene from a single RGB
+image or casual RGB video. The output contains object-level pose, geometry,
+and material assets that can be rendered, edited, and used in simulation.
+
+![Fire3D end-to-end perception and reconstruction method.](assets/method_overview.png)
+
+**Method overview.** Fire3D lifts RGB-D observations into a shared 3D scene
+representation, predicts object instances and 6-DoF poses, and reconstructs
+the sparse structure, shape, and PBR fields with three cascaded flow-matching
+models. Batched decoders and mesh post-processing produce the final textured
+scene assets.
+
+![Fire3D Hierarchical Compression VAE architecture.](assets/hcvae.png)
+
+**HC-VAE.** The Hierarchical Compression VAE reduces each sparse SC-VAE shape
+or material field from a `32^3 x 32` representation to an `8^3 x 64` latent.
+This 32x reduction makes scene-level batched flow sampling practical while
+retaining the frozen TRELLIS.2 decoding path.
+
 ## Model Bundle
 
 The repository contains the scene perception checkpoint, the three
@@ -54,8 +77,7 @@ frozen TRELLIS.2 SC-VAE decoding path.
 | TRELLIS.2 PBR decoder | `external/trellis2/tex_dec_next_dc_f16c32_fp16.safetensors` |
 
 Public filenames intentionally do not encode private training iteration
-numbers. The current method and HC-VAE figures are available in the
-[GitHub release](https://github.com/xiahongchi/Fire3D#method).
+numbers.
 
 The default protocols use classifier-free guidance 3, flow and VAE batches of
 16, and the batch CuMesh postprocessor. The iTHOR, Imaginarium, and ScanNet++