Presentation

<
Diffusing Winding Gradients (DWG): A Parallel and Scalable Method for 3D Reconstruction from Unoriented Point Clouds
SessionReconstruction & Neural Fields
DescriptionDiffusing Winding Gradients (DWG) efficiently reconstructs watertight 3D surfaces from unoriented point clouds. Unlike conventional methods, DWG avoids solving linear systems or optimizing objective functions, enabling simple implementation and parallel execution. Our CUDA implementation on an NVIDIA GTX 4090 GPU runs 30–120x faster than iPSR on large-scale models (10–20 million points).
Authors
Weizhou Liu
Beijing Normal University
Jiaze Li
Nanyang Technological University
Xuhui Chen
Institute of Software, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Fei Hou
Institute of Software, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Shiqing Xin
Shandong University
Xingce Wang
Beijing Normal University
Zhongke Wu
Beijing Normal University
Chen Qian
SenseTime Group
Ying He
Nanyang Technological University College of Computing and Data Science
Presenter
Ying He
Nanyang Technological University, School of Computer Science and Engineering
Event Type
Technical Paper
TimeTuesday, 12 August 20252:30pm - 2:40pm PDT
LocationWest Building, Rooms 211-214
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Tuesday, 12 August 20252:00pm - 3:30pm PDTWest Building, Rooms 211-214
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Registration Categories
Full Conference
Virtual Access
Tuesday
Next PresentationNext PresentationVariational Surface Reconstruction Using Natural Neighbors
Similar Presentations
Faraday Cage Estimation of Normals for Point Clouds and Ribbon Sketches
A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds with 0-1 Integer Optimization
IMLS-Splatting: Efficient Mesh Reconstruction from Multi-view Images via Point Representation