Papers
arxiv:2404.03566

PointInfinity: Resolution-Invariant Point Diffusion Models

Published on Apr 4
· Submitted by akhaliq on Apr 5
Authors:
,
,
,

Abstract

We present PointInfinity, an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size, resolution-invariant latent representation. This enables efficient training with low-resolution point clouds, while allowing high-resolution point clouds to be generated during inference. More importantly, we show that scaling the test-time resolution beyond the training resolution improves the fidelity of generated point clouds and surfaces. We analyze this phenomenon and draw a link to classifier-free guidance commonly used in diffusion models, demonstrating that both allow trading off fidelity and variability during inference. Experiments on CO3D show that PointInfinity can efficiently generate high-resolution point clouds (up to 131k points, 31 times more than Point-E) with state-of-the-art quality.

Community

There is something inherently satisfying about a diffusion model gradually materialising a 3D point cloud

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2404.03566 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2404.03566 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2404.03566 in a Space README.md to link it from this page.

Collections including this paper 16