Point-MF: One-step Point Cloud Generation from a Single Image via Mean Flows

• URL: http://arxiv.org/abs/2604.24586v1
• Date: Mon, 27 Apr 2026 15:10:47 GMT
• Title: Point-MF: One-step Point Cloud Generation from a Single Image via Mean Flows
• Abstract summary: Single-image point cloud reconstruction must infer complete 3D geometry, including occluded parts, from a single RGB image.<n>We propose Point-MF, a Mean-Flow-based framework for low-NFE single-image point cloud reconstruction.
• Score: 4.719615308536812
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 $x_θ$ 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.

Related papers

• Hierarchical Flow Matching for 3D Point Cloud Generation [3.451986888321395]
  Existing flow-based methods rely on continuous normalizing flows (CNFs) that demand expensive ODE solving and trace estimation during training.<n>We propose Hierarchical Flow Matching (HFM) that extends flow matching to bilevel structure for unconditional 3D point cloud generation.<n>The resulting straight OT paths enable efficient sampling with as few as 15 Euler steps per flow, while the structured latent space supports downstream tasks including classification.
  arXiv  Detail & Related papers  (2026-08-06T03:23:49Z)
• ZID-Net: Zero-Inference Diffusion Prior Decoupling Network for Single Image Dehazing [10.634107398163676]
  Single image dehazing is often constrained by a trade-off between restoration quality and computational efficiency.<n>ZID-Net is a novel framework that explicitly decouples diffusion supervision from feed-forward inference.<n>ZID-Net achieves 40.75 dB PSNR on the synthetic RESIDE dataset and outperforms existing methods with a 1.13 dB gain on real-world datasets.
  arXiv  Detail & Related papers  (2026-04-26T13:44:25Z)
• RAFT-MSF++: Temporal Geometry-Motion Feature Fusion for Self-Supervised Monocular Scene Flow [51.43025173196566]
  Monocular scene flow estimation aims to recover dense 3D motion from image sequences.<n>We propose RAFT-MSF++, a self-supervised multi-frame framework that fuses temporal features to jointly estimate depth and scene flow.<n>Experiments show that RAFT-MSF++ achieves 24.14% SF-all on the KITTI Scene Flow benchmark, with a 30.99% improvement over the baseline and better robustness in occluded regions.
  arXiv  Detail & Related papers  (2026-04-21T11:32:49Z)
• PUFM++: Point Cloud Upsampling via Enhanced Flow Matching [15.738247394527024]
  PUFM++ is an enhanced flow-matching framework for reconstructing point clouds from sparse, noisy, and partial observations.<n>We introduce a two-stage flow-matching strategy that first learns a direct, straight-path flow from sparse inputs to dense targets, and then refines it using noise-perturbed samples to approximate the terminal marginal distribution better.<n>Experiments on synthetic benchmarks and real-world scans show that PUFM++ sets a new state of the art in point cloud upsampling.
  arXiv  Detail & Related papers  (2025-12-24T06:30:42Z)
• MeanFlow Transformers with Representation Autoencoders [71.45823902973349]
  MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data.<n>We develop an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE)<n>We achieve a 1-step FID of 2.03, outperforming vanilla MF's 3.43, while reducing sampling GFLOPS by 38% and total training cost by 83% on ImageNet 256.
  arXiv  Detail & Related papers  (2025-11-17T06:17:08Z)
• FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systems [51.15230303652732]
  FLEX (F Low EXpert) is a backbone architecture for generative modeling of-temporal physical systems.<n>It reduces the variance of the velocity field in the diffusion model, which helps stabilize training.<n>It achieves accurate predictions for super-resolution and forecasting tasks using as few features as two reverse diffusion steps.
  arXiv  Detail & Related papers  (2025-05-23T00:07:59Z)
• FOF-X: Towards Real-time Detailed Human Reconstruction from a Single Image [64.96903230497755]
  We introduce FOF-X for real-time reconstruction of detailed human geometry from a single image.<n>The core of FOF is to factorize a 3D occupancy field into a 2D vector field, retaining topology and spatial relationships within the 3D domain.<n>Based on FOF, we design a new reconstruction framework, FOF-X, to avoid the performance degradation caused by texture and lighting.
  arXiv  Detail & Related papers  (2024-12-08T14:46:29Z)
• CCD-3DR: Consistent Conditioning in Diffusion for Single-Image 3D Reconstruction [81.98244738773766]
  We present CCD-3DR, which exploits a novel centered diffusion probabilistic model for consistent local feature conditioning. CCD-3DR outperforms all competitors by a large margin, with over 40% improvement.
  arXiv  Detail & Related papers  (2023-08-15T15:27:42Z)
• A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion [69.32451612060214]
  Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
  arXiv  Detail & Related papers  (2021-12-07T06:59:06Z)
• Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing [4.723586858098229]
  ERRA-Net has an impressive speed, processing 1200x1600 HD quality images with an average runtime of 166.11 fps. We use cascaded MA blocks to extract high-frequency features step by step, and the Multi-layer attention fusion tail combines the shallow and deep features of the model to get the residual of the clean image.
  arXiv  Detail & Related papers  (2021-09-12T10:03:44Z)
• Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision [68.35777836993212]
  We propose a Pseudo-LiDAR point cloud network to generate temporally and spatially high-quality point cloud sequences. By exploiting the scene flow between point clouds, the proposed network is able to learn a more accurate representation of the 3D spatial motion relationship.
  arXiv  Detail & Related papers  (2020-06-20T03:11:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.