Presentation
SuperSDF:Sparse SDF Super-Resolution for Surface Extraction
DescriptionSuperSDF is a learning-based method for signed distance field super-resolution that reconstructs high-fidelity meshes from coarse inputs, without mesh supervision or auxiliary surface representations. Using a sparse voxel network near the surface, our approach learns how to directly refine the input SDF, outperforming prior methods in quality, efficiency, and scalability.
Event Type
Technical Paper
TimeMonday, 20 July 20263:55pm - 4:05pm PDT
LocationRoom 408 B
Digital Library
PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Monday, 20 July 20263:45pm - 5:35pm PDTRoom 408 B
Artificial Intelligence/Machine Learning
Geometry
Full Conference Supporter
Full Conference
