no code implementations • 16 Mar 2024 • Dongyu Yan, Guanyu Huang, Fengyu Quan, Haoyao Chen
We first construct a multi-sphere image as a cost volume through feature extraction and warping of the input images.
no code implementations • 29 Mar 2023 • Dongyu Yan, Jianheng Liu, Fengyu Quan, Haoyao Chen, Mengmeng Fu
To evaluate view uncertainty, we employ a sampling-based approach that directly extracts entropy from the reconstructed occupancy probability field as our measure of view information gain.
1 code implementation • ICCV 2023 • Xiaoyang Lyu, Peng Dai, Zizhang Li, Dongyu Yan, Yi Lin, Yifan Peng, Xiaojuan Qi
We found that the color rendering loss results in optimization bias against low-intensity areas, causing gradient vanishing and leaving these areas unoptimized.
no code implementations • 28 Feb 2023 • Dongyu Yan, Xiaoyang Lyu, Jieqi Shi, Yi Lin
Modeling scene geometry using implicit neural representation has revealed its advantages in accuracy, flexibility, and low memory usage.