@inproceedings{b37f81499ea247418bef3d404694ab56,
title = "PointInfinity: Resolution-Invariant Point Diffusion Models",
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× more than Point-E) with state-of-the-art quality.",
keywords = "3D Diffusion Model, 3D Generation, 3D reconstruction, 3D Vision, Computer Vision, Deep Learning",
author = "Zixuan Huang and Justin Johnson and Shoubhik Debnath and Rehg, {James M.} and Wu, {Chao Yuan}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 ; Conference date: 16-06-2024 Through 22-06-2024",
year = "2024",
doi = "10.1109/CVPR52733.2024.00958",
language = "English (US)",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "10050--10060",
booktitle = "Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024",
address = "United States",
}