Publication | ACM SIGGRAPH 2023
Neural Shape Diameter Function for Efficient Mesh Segmentation
Abstract
Neural Shape Diameter Function for Efficient Mesh Segmentation
Bruno Roy
ACM SIGGRAPH 2023
Partitioning a polygonal mesh into meaningful parts can be challenging. Many applications require decomposing such structures for further processing in computer graphics. In the last decade, several methods were proposed to tackle this problem, at the cost of intensive computational times. Recently, machine learning has proven to be effective for the segmentation task on 3D structures. Nevertheless, these state-of-the-art methods are often hardly generalizable and require dividing the learned model into several specific classes of objects to avoid overfitting. We present a data-driven approach leveraging deep learning to encode a mapping function prior to mesh segmentation for multiple applications. Our network reproduces a neighborhood map using our knowledge of the Shape Diameter Function (SDF) method using similarities among vertex neighborhoods. Our approach is resolution-agnostic as we downsample the input meshes and query the full-resolution structure solely for neighborhood contributions. Using our predicted SDF values, we can inject the resulting structure into a graph-cut algorithm to generate an efficient and robust mesh segmentation while considerably reducing the required computation times.
Download publicationRelated Resources
2024
Highlights from our Interns: What They Loved about their InternshipsWe asked our summer internships to share what they most enjoyed about…
2024
ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical FeasibilityA physics-based planning approach for automatically generating…
2023
Multi-split configuration design for fluid-based thermal management systemsThis work introduces a framework for automated exploration of optimal…
2019
Unsupervised Multi-Task Feature Learning on Point CloudsWe introduce an unsupervised multi-task model to jointly learn point…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us