Quewei Li — accepted AI-conference papers

2023

UHDNeRF: Ultra-High-Definition Neural Radiance Fields

Quewei Li, Feichao Li, Jie Guo, Yanwen Guo

ICCV 2023poster

We propose UHDNeRF, a new framework for novel view synthesis on the challenging ultra-high-resolution (e.g., 4K) real-world scenes. Previous NeRF methods are not specifically designed for rendering on extremely high resolutions, leading to burry results with notable detail-losing problems even thoug…

Cited by 11 PDF ↗Scholar ↗

2020

Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention

Quewei Li, Jie Guo, Yang Fei, Qinyu Tang, Wenxiu Sun, Jin Zeng +1

ECCV 2020poster

We propose a deep convolutional neural network (CNN) to estimate surface normal from a single color image accompanied with a low-quality depth channel. Unlike most previous works, we predict the normal on the 2-sphere rather than the 3D Euclidean space, which produces naturally normalized values and…

Cited by 3 Source ↗PDF ↗Scholar ↗