De‐NeRF: Ultra‐high‐definition NeRF with deformable net alignment

• Published in: Computer animation and virtual worlds Vol. 35; no. 3
• Main Authors: Hou, Jianing, Zhang, Runjie, Wu, Zhongqi, Meng, Weiliang, Zhang, Xiaopeng, Guo, Jianwei
• Format: Journal Article
• Language: English
• Published: Chichester Wiley Subscription Services, Inc 01.05.2024
• Subjects: Data smoothing; deformable convolution net; Deformation effects; Formability; High resolution; Misalignment; neural radiance fields; Rendering; Visual effects; voxel‐based embedding
• ISSN: 1546-4261; 1546-427X
• DOI: 10.1002/cav.2240

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 of high‐frequency details and achieves better visual effects in 4K high‐resolution scenes. We present a novel framework, De‐NeRF, for achieving high‐fidelity view synthesis in ultra‐high resolution scenes. The key technical components of De‐NeRF includes a hybrid volumetric representation that can significantly speed up the training, and a deformable alignment unit module that can solve the problem of misaligned input of the high‐resolution data.