← Search

Yu-Tao Liu

2 accepted papers

2025

NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation

ICCV 2025poster

Quad meshes play a crucial role in computer graphics applications, yet automatically generating high-quality quad meshes remains challenging. Traditional quadrangulation approaches rely on local geometric features and manual constraints, often producing suboptimal mesh layouts that fail to capture g…

Cited by 0SourcePDFScholar
2023

NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering

CVPR 2023poster

Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering. However, existing methods based on signed distance function (SDF) are limited to closed surfaces, failing to reconstruct a wide range of real-world objects that cont…

Cited by 58SourcePDFScholar