Skip to yearly menu bar Skip to main content


PointInfinity: Resolution-Invariant Point Diffusion Models

Zixuan Huang · Justin Johnson · Shoubhik Debnath · James Rehg · Chao-Yuan Wu

Arch 4A-E Poster #38
[ ] [ Project Page ]
Thu 20 Jun 10:30 a.m. PDT — noon PDT


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.

Live content is unavailable. Log in and register to view live content