Point Cloud Smoother for 3D Noise Removal and Detail Preservation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing 3D scanning techniques produce noisy 3D models due to noise during the scanning process, leading to removal of fine details and surface shrinkage or drifting when attempting to denoise these models.

Innovation Solution

The Point Cloud Smoother employs robust plane fitting and estimation techniques to refine 3D point clouds by projecting points onto fitted planes and computing new normals, effectively generating a smoothed and denoised 3D output model while preserving fine details.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If mesh smoothing is applied to denoise the 3D surface, then noise is removed, but fine details of 3D features are blurred out

Engineering Contradiction:

Improvenoise removalVSAvoidfine detail preservation

Core Design Contradiction:

ReliabilityVSManufacturing precision

Solution Approach 1:

The patent applies different smoothing strengths to different regions of the 3D surface based on local curvature and feature detection. High-curvature regions (sharp edges, corners) are protected from smoothing while low-curvature regions undergo stronger denoising, allowing noise removal without blurring fine details through localized adaptive processing

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent segments the 3D surface into multiple regions based on geometric features and processes each region independently with appropriate smoothing parameters. This segmentation allows simultaneous denoising in flat regions while preserving sharp features in curved regions, resolving the contradiction between noise removal and detail preservation

Inventive Principle:

Principle #1Segmentation

2Reliability

If mesh smoothing is applied to denoise the 3D surface, then noise is removed, but shrinkage or drifting of the 3D surfaces occurs

Engineering Contradiction:

Improvenoise removalVSAvoidsurface position accuracy

Core Design Contradiction:

ReliabilityVSShape

Solution Approach 1:

The patent implements feedback mechanisms that continuously monitor the 3D surface geometry during smoothing and adjust processing parameters to prevent shrinkage. When surface deformation is detected, the algorithm adapts its smoothing strength and position constraints to maintain surface integrity while still removing noise

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent applies beforehand cushioning by establishing geometric constraints and anchor points before smoothing begins. These pre-established reference structures prevent surface shrinkage and drifting during the denoising process, allowing noise removal while maintaining accurate surface positions

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Data Source

PatentUS9767598B2Smoothing and robust normal estimation for 3D point clouds

Publication Date: 2017.09.19 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

A “Point Cloud Smoother” provides various techniques for refining a 3D point cloud or other 3D input model to generate a smoothed and denoised 3D output model. Smoothing and denoising is achieved, in part, by robustly fitting planes to a neighborhood of points around each point of the input model and using those planes to estimate new points and corresponding normals of the 3D output model. These techniques are useful for a number of purposes, including, but not limited to, free viewpoint video (FVV), which, when combined with the smoothing techniques enabled by the Point Cloud Smoother, allows 3D data of videos or images to be denoised and then rendered and viewed from any desired viewpoint that is supported by the input data.