Abstract
Kernel Surface Reconstruction (NKSR) recovers a 3D surface from an input point cloud.Trained directly from dense points, our method reaches state-of-the-art reconstruction quality and scalability. All the meshes in this figure are reconstructed using a single trained model.
Speaker
Jiahui Huang is currently a research scientist at NVIDIA Toronto AI Lab, which is led by Sanja Fidler. He received his Ph.D. in 2023 from the Graphics and Geometric Computing Group at Tsinghua University, China, under the advisement of Shi-Min Hu. Additionally, Huang served as a visiting researcher in the Geometric Computing group at Stanford University, which is led by Leonidas Guibas. His primary research interests lie in the joint field of 3D computer vision and graphics, which encompasses neural reconstruction, dynamic scene perception, and SLAM.
Video
Extra Details
Speaker Website / Paper Link / Paper Project Page / Paper Video / Paper Code