From 12df7f9308e5ce4f2d25837ac52d5fa85b4b7564 Mon Sep 17 00:00:00 2001 From: kkreis Date: Fri, 7 Oct 2022 10:48:18 -0700 Subject: [PATCH] minor fixes --- assets/zeng2022lion.bib | 6 ++++++ index.html | 27 +++++++++++++-------------- 2 files changed, 19 insertions(+), 14 deletions(-) create mode 100644 assets/zeng2022lion.bib diff --git a/assets/zeng2022lion.bib b/assets/zeng2022lion.bib new file mode 100644 index 0000000..fcbe223 --- /dev/null +++ b/assets/zeng2022lion.bib @@ -0,0 +1,6 @@ +@inproceedings{zeng2022lion, + title={LION: Latent Point Diffusion Models for 3D Shape Generation}, + author={Xiaohui Zeng and Arash Vahdat and Francis Williams and Zan Gojcic and Or Litany and Sanja Fidler and Karsten Kreis}, + booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, + year={2022} +} \ No newline at end of file diff --git a/index.html b/index.html index b7385df..c0d21bb 100644 --- a/index.html +++ b/index.html @@ -345,7 +345,7 @@ pre {

LION: - Latent Point Diffusion Models
for 3D Shape Generation

+ Latent Point Diffusion Models
for 3D Shape Generation
@@ -409,7 +409,9 @@ pre {

News

-
event [Sept 2022] Build the project page Page!
+
event [Oct 2022] Project page released!
+
event [Oct 2022] Paper released on arXiv!
+
event [Aug 2022] LION got accepted to Advances in Neural Information Processing Systems (NeurIPS)!
@@ -426,8 +428,8 @@ pre { we train two hierarchical DDMs in these latent spaces. The hierarchical VAE approach boosts performance compared to DDMs that operate on point clouds directly, while the point-structured latents are still ideally suited for DDM-based modeling. Experimentally, LION achieves state-of-the-art generation performance on multiple ShapeNet benchmarks. Furthermore, our VAE framework allows us to easily - use LION for different relevant tasks without re-training the latent DDMs: We show that LION excels at multimodal shape denoising and - voxel-conditioned synthesis. We also demonstrate shape autoencoding and latent shape interpolation, and we augment LION with modern + use LION for different relevant tasks: LION excels at multimodal shape denoising and voxel-conditioned synthesis, and it can be adapted + for text- and image-driven 3D generation.. We also demonstrate shape autoencoding and latent shape interpolation, and we augment LION with modern surface reconstruction techniques to generate smooth 3D meshes. We hope that LION provides a powerful tool for artists working with 3D shapes due to its high-quality generation, flexibility, and surface reconstruction.

@@ -777,12 +779,10 @@ pre {

LION: Latent Point Diffusion Models for 3D Shape Generation

Xiaohui Zeng, Arash Vahdat, Francis Williams, Zan Gojcic, Or Litany, Sanja Fidler, Karsten Kreis

-

Advances in Neural Information Processing Systems (NeurIPS), 2022

- +

Advances in Neural Information Processing Systems (NeurIPS), 2022

+
description arXiv version
+
insert_comment BibTeX
+
integration_instructions Code
@@ -791,10 +791,9 @@ pre {

Citation

- 
@inproceedings{ 
-    zeng2022lion,
-    title={ LION: Latent Point Diffusion Models for 3D Shape Generation },
-    author={ Xiaohui Zeng and Arash Vahdat and Francis Williams and Zan Gojcic and Or Litany and Sanja Fidler and Karsten Kreis },
+        
@inproceedings{zeng2022lion,
+    title={LION: Latent Point Diffusion Models for 3D Shape Generation},
+    author={Xiaohui Zeng and Arash Vahdat and Francis Williams and Zan Gojcic and Or Litany and Sanja Fidler and Karsten Kreis},
     booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
     year={2022}
 }