Fast Point Cloud Generation with Straight Flows
This work addresses latency constraints for 3D real-world applications like point cloud completion and text-guided generation, offering an incremental improvement in efficiency.
The paper tackles the problem of slow point cloud generation in diffusion models by proposing Point Straight Flow (PSF), which reformulates the diffusion process into a straight path and uses distillation to achieve one-step generation, performing comparably to standard diffusion models and outperforming other efficient methods in 3D tasks.
Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While beneficial, the complexity of learning steps has limited its applications to many 3D real-world. To address this limitation, we propose Point Straight Flow (PSF), a model that exhibits impressive performance using one step. Our idea is based on the reformulation of the standard diffusion model, which optimizes the curvy learning trajectory into a straight path. Further, we develop a distillation strategy to shorten the straight path into one step without a performance loss, enabling applications to 3D real-world with latency constraints. We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods. On real-world applications such as point cloud completion and training-free text-guided generation in a low-latency setup, PSF performs favorably.