Knowledge Commons of Institute of Automation,CAS
De-NeRF: Ultra-High-Definition NeRF with Deformable Net Alignment | |
Hou JN(侯佳宁)1,2; Runjie Zhang3; Zhongqi Wu4; Meng WL(孟维亮)1,2; Zhang XP(张晓鹏)1,2; Guo JW(郭建伟)1,2 | |
发表期刊 | Computer Animation and Virtual Worlds |
2024 | |
卷号 | 35期号:3页码:1-14 |
摘要 | Neural Radiance Field (NeRF) can render complex 3D scenes with viewpoint-dependent effects. However, less work has been devoted to exploring its limitations in high-resolution environments, especially when upscaled to ultra-high resolution (e.g., 4k). Specifically, existing NeRF-based methods face severe limitations in reconstructing high-resolution real scenes, for example, a large number of parameters, misalignment of the input data, and over-smoothing of details. In this paper, we present a novel and effective framework, called De-NeRF, based on NeRF and deformable convolutional network, to achieve high-fidelity view synthesis in ultra-high resolution scenes: (1) marrying the deformable convolution unit which can solve the problem of misaligned input of the high-resolution data. (2) Presenting a density sparse voxel-based approach which can greatly reduce the training time while rendering results with higher accuracy. Compared to existing high-resolution NeRF methods, our approach improves the rendering quality ofhigh-frequency details and achieves better visual effects in 4K high-resolution scenes. |
语种 | 中文 |
WOS记录号 | WOS:001235192800001 |
七大方向——子方向分类 | 计算机图形学与虚拟现实 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57167 |
专题 | 多模态人工智能系统全国重点实验室_三维可视计算 |
通讯作者 | Guo JW(郭建伟) |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 2.State Key Laboratory ofMultimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China 3.UC San Diego, University of California San Diego, La Jolla, California, USA 4.Institutes of Science and Development, Chinese Academy of Sciences, Beijing, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Hou JN,Runjie Zhang,Zhongqi Wu,et al. De-NeRF: Ultra-High-Definition NeRF with Deformable Net Alignment[J]. Computer Animation and Virtual Worlds,2024,35(3):1-14. |
APA | Hou JN,Runjie Zhang,Zhongqi Wu,Meng WL,Zhang XP,&Guo JW.(2024).De-NeRF: Ultra-High-Definition NeRF with Deformable Net Alignment.Computer Animation and Virtual Worlds,35(3),1-14. |
MLA | Hou JN,et al."De-NeRF: Ultra-High-Definition NeRF with Deformable Net Alignment".Computer Animation and Virtual Worlds 35.3(2024):1-14. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
10.1002_cav.2240.pdf(3020KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论