PointInfinity: Resolution-Invariant Point Diffusion Models

Zixuan Huang, Justin Johnson, Shoubhik Debnath, James M. Rehg, Chao-Yuan Wu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 10050-10060

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.