Hybrid Long and Short Range Flows for Point Cloud Filtering

• URL: http://arxiv.org/abs/2508.08542v1
• Date: Tue, 12 Aug 2025 01:11:22 GMT
• Title: Hybrid Long and Short Range Flows for Point Cloud Filtering
• Authors: Dasith de Silva Edirimuni, Xuequan Lu, Ajmal Saeed Mian, Lei Wei, Gang Li, Scott Schaefer, Ying He,
• Abstract summary: Point cloud capture processes are error-prone and introduce noisy artifacts that necessitate filtering/denoising.<n>Recent filtering methods often suffer from point clustering or noise retaining issues.<n>We propose Hybrid Point Cloud Filtering that considers both short-range and long-range filtering trajectories.
• Score: 13.976176051536275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud capture processes are error-prone and introduce noisy artifacts that necessitate filtering/denoising. Recent filtering methods often suffer from point clustering or noise retaining issues. In this paper, we propose Hybrid Point Cloud Filtering ($\textbf{HybridPF}$) that considers both short-range and long-range filtering trajectories when removing noise. It is well established that short range scores, given by $\nabla_{x}\log p(x_t)$, may provide the necessary displacements to move noisy points to the underlying clean surface. By contrast, long range velocity flows approximate constant displacements directed from a high noise variant patch $x_0$ towards the corresponding clean surface $x_1$. Here, noisy patches $x_t$ are viewed as intermediate states between the high noise variant and the clean patches. Our intuition is that long range information from velocity flow models can guide the short range scores to align more closely with the clean points. In turn, score models generally provide a quicker convergence to the clean surface. Specifically, we devise two parallel modules, the ShortModule and LongModule, each consisting of an Encoder-Decoder pair to respectively account for short-range scores and long-range flows. We find that short-range scores, guided by long-range features, yield filtered point clouds with good point distributions and convergence near the clean surface. We design a joint loss function to simultaneously train the ShortModule and LongModule, in an end-to-end manner. Finally, we identify a key weakness in current displacement based methods, limitations on the decoder architecture, and propose a dynamic graph convolutional decoder to improve the inference process. Comprehensive experiments demonstrate that our HybridPF achieves state-of-the-art results while enabling faster inference speed.

Related papers

• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• 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)
• EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion Models [57.059991285047296]
  hybrid edge-cloud collaborative framework was recently proposed to realize fast inference and high-quality generation.<n>Excessive cloud denoising prolongs inference time, while insufficient steps cause semantic ambiguity, leading to inconsistency in edge model output.<n>We propose EC-Diff that accelerates cloud inference through gradient-based noise estimation.<n>Our method significantly enhances generation quality compared to edge inference, while achieving up to an average $2times$ speedup in inference compared to cloud inference.
  arXiv  Detail & Related papers  (2025-07-16T07:23:14Z)
• Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Sampling [23.57202605415588]
  The rectified flow (RF) has emerged as the new state-of-the-art among flow-based diffusion models.<n>We present Discretized-RF, a new family of rectified flow models.<n>We introduce noise on the velocity $bm v$ of the sub-path to change its direction to improve the diversity and multi-scale noise modeling abilities.
  arXiv  Detail & Related papers  (2025-06-10T13:44:49Z)
• Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping [54.38209327518066]
  Learning signed distance functions from point clouds is an important task in 3D computer vision. We propose to learn SDFs via a noise to noise mapping, which does not require any clean point cloud or ground truth supervision. Our novelty lies in the noise to noise mapping which can infer a highly accurate SDF of a single object or scene from its multiple or even single noisy observations.
  arXiv  Detail & Related papers  (2024-07-04T03:35:02Z)
• StraightPCF: Straight Point Cloud Filtering [50.66412286723848]
  Point cloud filtering is a fundamental 3D vision task, which aims to remove noise while recovering the underlying clean surfaces. We introduce StraightPCF, a new deep learning based method for point cloud filtering. It works by moving noisy points along straight paths, thus reducing discretization errors while ensuring faster convergence to the clean surfaces.
  arXiv  Detail & Related papers  (2024-05-14T05:41:59Z)
• IterativePFN: True Iterative Point Cloud Filtering [18.51768749680731]
  A fundamental 3D vision task is the removal of noise, known as point cloud filtering or denoising. We propose IterativePFN (iterative point cloud filtering network), which consists of multiple Iterations that model the true iterative filtering process internally. Our method is able to obtain better performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-04-04T04:47:44Z)
• Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining [61.09807522366773]
  We introduce an algorithm that approximates the softmax with provable bounds and that dynamically maintains the tree. In our study on datasets with over twenty million targets, our approach cuts error by half in relation to oracle brute-force negative mining.
  arXiv  Detail & Related papers  (2023-03-27T15:18:32Z)
• PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling [56.463507980857216]
  We propose a generative adversarial network for point cloud upsampling. It can make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions.
  arXiv  Detail & Related papers  (2022-03-02T07:47:46Z)
• Score-Based Point Cloud Denoising [26.090445369658312]
  Point clouds acquired from scanning devices are often perturbed by noise, which affects downstream tasks such as surface reconstruction and analysis. We propose to increase the log-likelihood of each point from $p * n$ via gradient ascent -- iteratively updating each point's position. We derive objective functions for training the network and develop a denoising algorithm leveraging on the estimated scores.
  arXiv  Detail & Related papers  (2021-07-23T01:13:03Z)
• Learning to Estimate Hidden Motions with Global Motion Aggregation [71.12650817490318]
  Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We introduce a global motion aggregation module to find long-range dependencies between pixels in the first image. We demonstrate that the optical flow estimates in the occluded regions can be significantly improved without damaging the performance in non-occluded regions.
  arXiv  Detail & Related papers  (2021-04-06T10:32:03Z)

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.