Výsledky vyhledávání - "Shao, Mingqi"

Report

Global-guided Focal Neural Radiance Field for Large-scale Scene Rendering

Autor: Shao, Mingqi, Xiong, Feng, Zhang, Hang, Yang, Shuang, Xu, Mu, Bian, Wei, Wang, Xueqian

Neural radiance fields~(NeRF) have recently been applied to render large-scale scenes. However, their limited model capacity typically results in blurred rendering results. Existing large-scale NeRFs primarily address this limitation by partitioning

Externí odkaz: http://arxiv.org/abs/2403.12839

Zobrazit plný text záznamu

Report

Polarimetric Inverse Rendering for Transparent Shapes Reconstruction

Autor: Shao, Mingqi, Xia, Chongkun, Duan, Dongxu, Wang, Xueqian

In this work, we propose a novel method for the detailed reconstruction of transparent objects by exploiting polarimetric cues. Most of the existing methods usually lack sufficient constraints and suffer from the over-smooth problem. Hence, we introd

Externí odkaz: http://arxiv.org/abs/2208.11836

Zobrazit plný text záznamu

Report

Masked Generative Distillation

Autor: Yang, Zhendong, Li, Zhe, Shao, Mingqi, Shi, Dachuan, Yuan, Zehuan, Yuan, Chun

Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve students' represe

Externí odkaz: http://arxiv.org/abs/2205.01529

Zobrazit plný text záznamu

Report

Transparent Shape from a Single View Polarization Image

Autor: Shao, Mingqi, Xia, Chongkun, Yang, Zhendong, Huang, Junnan, Wang, Xueqian

This paper presents a learning-based method for transparent surface estimation from a single view polarization image. Existing shape from polarization(SfP) methods have the difficulty in estimating transparent shape since the inherent transmission in

Externí odkaz: http://arxiv.org/abs/2204.06331

Zobrazit plný text záznamu