TY - GEN
T1 - SDFConnect
T2 - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
AU - Jignasu, Anushrut
AU - Balu, Aditya
AU - Sarkar, Soumik
AU - Hegde, Chinmay
AU - Ganapathysubramanian, Baskar
AU - Krishnamurthy, Adarsh
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - We present a novel approach for neural implicit surface reconstruction from relatively sparse point cloud to ensure the reconstruction of a single connected component. We introduce a topological loss term based on persistent homology to reconstruct a manifold object of genus 1. Building on the Neural Pull [25] framework, our method demonstrates superior performance in preserving the integrity of complex 3D geometries, evident through both visual and empirical comparisons. Our contributions include the integration of persistent diagrams to refine shape topology and a topological loss term to constrain existing reconstruction pipelines to a single connected component. This advancement allows for the seamless integration of topological data analysis with implicit surface reconstruction.
AB - We present a novel approach for neural implicit surface reconstruction from relatively sparse point cloud to ensure the reconstruction of a single connected component. We introduce a topological loss term based on persistent homology to reconstruct a manifold object of genus 1. Building on the Neural Pull [25] framework, our method demonstrates superior performance in preserving the integrity of complex 3D geometries, evident through both visual and empirical comparisons. Our contributions include the integration of persistent diagrams to refine shape topology and a topological loss term to constrain existing reconstruction pipelines to a single connected component. This advancement allows for the seamless integration of topological data analysis with implicit surface reconstruction.
KW - persistent homology
KW - signed distance fields
KW - surface reconstruction
KW - topological data analysis
UR - http://www.scopus.com/inward/record.url?scp=85206477727&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85206477727&partnerID=8YFLogxK
U2 - 10.1109/CVPRW63382.2024.00536
DO - 10.1109/CVPRW63382.2024.00536
M3 - Conference contribution
AN - SCOPUS:85206477727
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 5271
EP - 5279
BT - Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
PB - IEEE Computer Society
Y2 - 16 June 2024 through 22 June 2024
ER -