Search papers, labs, and topics across Lattice.
This paper introduces Point-MF, a novel framework for single-image point cloud reconstruction that leverages Mean Flows to achieve one-step generation. By operating directly in point cloud space and learning the mean velocity field, Point-MF avoids the slow, iterative denoising process of diffusion models. The method incorporates a Diffusion Transformer conditioned on DINOv3 features and a Denoised Space Anchor loss to stabilize large-step generation, resulting in high-quality point clouds with millisecond-level latency.
Achieve millisecond-level 3D point cloud reconstruction from a single image without sacrificing quality, blowing past diffusion model latency.
Single-image point cloud reconstruction must infer complete 3D geometry, including occluded parts, from a single RGB image. While diffusion-based reconstructors achieve high accuracy, they typically require many denoising iterations, resulting in slow and expensive inference. We propose Point-MF, a Mean-Flow-based framework for low-NFE single-image point cloud reconstruction that couples a Mean-Flow-compatible architecture with an auxiliary loss. Specifically, Point-MF operates directly in point-cloud space to learn the mean velocity field and enables one-step reconstruction with a single network function evaluation (1-NFE), without relying on VAE-based latent representations. To make Mean Flow effective under large interval jumps, Point-MF employs a Diffusion Transformer tailored to the Mean-Flow setting, conditioned on frozen DINOv3 image features via a lightweight token adapter and equipped with explicit interval/time conditioning. Moreover, we introduce Denoised Space Anchor, a set-distance auxiliary loss on the denoised-space estimate $x_\theta$ induced by the predicted velocity field, to stabilize large-step generation and reduce outliers and density artifacts. On ShapeNet-R2N2 and Pix3D, Point-MF strikes a strong balance between reconstruction quality and inference speed compared to multi-step diffusion baselines and competitive feedforward models, while generating high-quality point clouds with millisecond-level latency.
