|
Lihan Li Hi, I'm Lihan Li (李砺涵), a student at Peking University, specifically at Yuanpei College. My research interests and hobbies are detailed in my CV. I'm passionate about exploring the intersection of 3D computer vision, computer graphics. |
|
🔥 News
|
PublicationView my papers and projects here. |
|
PointCNN++: Performant Convolution on Native Points
L. Li, H. Zhong, R. Bu, M. Sun, W. Chen, B. Chen, Y. Li arXiv:2511.23227 paper Existing convolutional learning methods for 3D point cloud data are divided into two paradigms: point-based methods that preserve geometric precision but often face performance challenges, and voxel-based methods that achieve high efficiency through quantization at the cost of geometric fidelity. We propose PointCNN++, a novel architectural design that fundamentally mitigates this precision-performance trade-off by generalizing sparse convolution from voxels to points, treating voxel-based convolution as a specialized, degraded case of our more general point-based convolution. |
|
Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding
J. Li, Q. Dai, L. Li, et al. SIGGRAPH Asia 2025 A learning-based structured light decoding framework utilizing neural feature embeddings for robust pixel correspondence, improving reconstruction accuracy in complex lighting and material conditions. |
|
Design from Jon Barron's web |