Refresh method and HC-VAE figures

.gitattributes

@@ -36,3 +36,5 @@ saved_model/**/* 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
+assets/hcvae.pdf filter=lfs diff=lfs merge=lfs -text
+assets/method_overview.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -34,7 +34,7 @@ inputs are hosted at
 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)
+[![Fire3D end-to-end perception and reconstruction method.](assets/method_overview.png)](assets/method_overview.pdf)
 
 **Method overview.** Fire3D lifts RGB-D observations into a shared 3D scene
 representation, predicts object instances and 6-DoF poses, and reconstructs
@@ -42,7 +42,7 @@ 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)
+[![Fire3D Hierarchical Compression VAE architecture.](assets/hcvae.png)](assets/hcvae.pdf)
 
 **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.

assets/hcvae.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac00a04a9339b1ee76705e658dd042ea5d6d2741141ae94a8160e6d6024ee472
+size 369594

assets/method_overview.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4cc27df14f97fccf3b46eb6a55626ba4b9ea818e01b50996006cce8855767de
+size 1523738