ComfyUI > Nodes > ComfyUI libigl > Reconstruct Surface

ComfyUI Node: Reconstruct Surface

Class Name

GeomPackReconstructSurface

Category
geompack/reconstruction
Author
PozzettiAndrea (Account age: 2240days)
Extension
ComfyUI libigl
Latest Updated
2025-12-22
Github Stars
0.06K

How to Install ComfyUI libigl

Install this extension via the ComfyUI Manager by searching for ComfyUI libigl
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI libigl in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Reconstruct Surface Description

Reconstructs 3D surfaces from point clouds using Poisson method for smooth, watertight meshes.

Reconstruct Surface:

The GeomPackReconstructSurface node is designed to reconstruct a 3D surface from a set of input points, typically a point cloud. This node leverages the Poisson surface reconstruction method provided by PyMeshLab, which is a powerful tool for creating smooth, watertight surfaces from scattered data points. The primary goal of this node is to transform raw point cloud data into a coherent mesh that can be used for further processing or visualization. By using this node, you can efficiently generate high-quality 3D models from point clouds, which is particularly beneficial for applications in 3D modeling, computer graphics, and AI art creation. The node is capable of estimating normals if they are not provided, ensuring that the reconstruction process is robust and adaptable to various input conditions.

Reconstruct Surface Input Parameters:

points

This parameter represents the input point cloud data that the node will use to reconstruct the surface. It is a collection of 3D points that define the shape of the object you wish to model. The quality and density of these points can significantly impact the final mesh's detail and accuracy.

method

The method parameter specifies the reconstruction technique to be used. In this context, the Poisson method is employed, which is well-suited for creating smooth and watertight surfaces. This parameter allows you to choose the most appropriate reconstruction strategy based on your specific needs.

poisson_depth

This parameter controls the depth of the Poisson reconstruction process. It determines the level of detail in the resulting mesh, with higher values producing more detailed surfaces. The default value is typically set to 8, but it can be adjusted to balance detail and computational cost.

poisson_scale

The poisson_scale parameter influences the scale of the reconstruction process. It affects the size of the features in the resulting mesh, with a default value of 1.1. Adjusting this parameter can help fine-tune the mesh's appearance to better match the input data.

ball_radius

This parameter is used in alternative reconstruction methods and is not directly applicable to the Poisson method. It defines the radius of influence for each point in the reconstruction process, affecting the smoothness and connectivity of the mesh.

alpha

Similar to ball_radius, the alpha parameter is relevant for other reconstruction techniques. It controls the level of detail and smoothness in the resulting mesh, with higher values producing smoother surfaces.

estimate_normals

This boolean parameter indicates whether the node should estimate normals for the input points if they are not provided. Estimating normals is crucial for accurate surface reconstruction, and enabling this option ensures that the node can handle point clouds without pre-computed normals.

normal_radius

The normal_radius parameter specifies the radius used for normal estimation when estimate_normals is enabled. It determines the neighborhood size for normal computation, affecting the accuracy and smoothness of the estimated normals.

Reconstruct Surface Output Parameters:

result

The result parameter is the primary output of the node, representing the reconstructed 3D mesh. This mesh is a collection of vertices and faces that define the surface of the object, and it can be used for visualization, further processing, or export to other formats.

info

The info parameter provides detailed information about the reconstruction process, including the engine used, the depth and scale settings, and statistics about the input and output data. This information is valuable for understanding the reconstruction's quality and for debugging purposes.

Reconstruct Surface Usage Tips:

  • Ensure that your input point cloud is dense enough to capture the details of the object you wish to reconstruct. Sparse point clouds may result in incomplete or inaccurate meshes.
  • Experiment with the poisson_depth and poisson_scale parameters to achieve the desired level of detail and smoothness in your reconstructed mesh. Higher depth values increase detail but also computational cost.
  • If your input data lacks normals, enable the estimate_normals option to ensure accurate surface reconstruction. Adjust the normal_radius parameter to fine-tune the normal estimation process.

Reconstruct Surface Common Errors and Solutions:

"MeshSet is empty"

  • Explanation: This error occurs when the input point cloud is not properly added to the MeshSet, possibly due to missing or incorrect data.
  • Solution: Verify that your input points are correctly formatted and that the point cloud is not empty. Ensure that the points parameter is populated with valid 3D coordinates.

"Poisson reconstruction failed"

  • Explanation: This error indicates that the Poisson reconstruction process encountered an issue, possibly due to inappropriate parameter settings or insufficient input data.
  • Solution: Check the poisson_depth and poisson_scale parameters to ensure they are set to reasonable values. Additionally, confirm that the input point cloud is dense and well-distributed.

Reconstruct Surface Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI libigl
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.