Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Hybrid Long and Short Range Flows for Point Cloud Filtering

About

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.

Dasith de Silva Edirimuni, Xuequan Lu, Ajmal Saeed Mian, Lei Wei, Gang Li, Scott Schaefer, Ying He• 2025

Related benchmarks

TaskDatasetResultRank
Point Cloud DenoisingPUNet Gaussian Noise (test)
Chamfer Distance (CD)4.9
114
Point Cloud DenoisingPCNet 10K points, 2% Gaussian noise
Chamfer Distance (CD)39.7
15
Point Cloud DenoisingPCNet 50K points 1% Gaussian noise
Chamfer Distance (CD)7.9
15
Point Cloud DenoisingPCNet 50K points, 2% Gaussian noise
Chamfer Distance (CD)11.2
15
Point Cloud DenoisingPCNet 10K points, 1% Gaussian noise
Chamfer Distance (CD)27.9
15
Point Cloud DenoisingPCNet 10K points, 3% Gaussian noise
Chamfer Distance (CD)49.9
15
Point Cloud DenoisingPCNet 50K points, 3% Gaussian noise
Chamfer Distance19.1
15
Showing 7 of 7 rows

Other info

Follow for update