2022-09-14 更新
StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints
Authors:Zheng Chen, Chen Wang, Yuan-Chen Guo, Song-Hai Zhang
Neural Radiance Fields (NeRF) achieve photo-realistic view synthesis with densely captured input images. However, the geometry of NeRF is extremely under-constrained given sparse views, resulting in significant degradation of novel view synthesis quality. Inspired by self-supervised depth estimation methods, we propose StructNeRF, a solution to novel view synthesis for indoor scenes with sparse inputs. StructNeRF leverages the structural hints naturally embedded in multi-view inputs to handle the unconstrained geometry issue in NeRF. Specifically, it tackles the texture and non-texture regions respectively: a patch-based multi-view consistent photometric loss is proposed to constrain the geometry of textured regions; for non-textured ones, we explicitly restrict them to be 3D consistent planes. Through the dense self-supervised depth constraints, our method improves both the geometry and the view synthesis performance of NeRF without any additional training on external data. Extensive experiments on several real-world datasets demonstrate that StructNeRF surpasses state-of-the-art methods for indoor scenes with sparse inputs both quantitatively and qualitatively.
PDF
点此查看论文截图
FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing
Authors:Jingbo Zhang, Xiaoyu Li, Ziyu Wan, Can Wang, Jing Liao
We propose a Few-shot Dynamic Neural Radiance Field (FDNeRF), the first NeRF-based method capable of reconstruction and expression editing of 3D faces based on a small number of dynamic images. Unlike existing dynamic NeRFs that require dense images as input and can only be modeled for a single identity, our method enables face reconstruction across different persons with few-shot inputs. Compared to state-of-the-art few-shot NeRFs designed for modeling static scenes, the proposed FDNeRF accepts view-inconsistent dynamic inputs and supports arbitrary facial expression editing, i.e., producing faces with novel expressions beyond the input ones. To handle the inconsistencies between dynamic inputs, we introduce a well-designed conditional feature warping (CFW) module to perform expression conditioned warping in 2D feature space, which is also identity adaptive and 3D constrained. As a result, features of different expressions are transformed into the target ones. We then construct a radiance field based on these view-consistent features and use volumetric rendering to synthesize novel views of the modeled faces. Extensive experiments with quantitative and qualitative evaluation demonstrate that our method outperforms existing dynamic and few-shot NeRFs on both 3D face reconstruction and expression editing tasks. Code is available at https://github.com/FDNeRF/FDNeRF.
PDF Accepted at SIGGRAPH Asia 2022. Project page: https://fdnerf.github.io
点此查看论文截图
Explicitly Controllable 3D-Aware Portrait Generation
Authors:Junshu Tang, Bo Zhang, Binxin Yang, Ting Zhang, Dong Chen, Lizhuang Ma, Fang Wen
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs and the state of the arts can now yield highly photo-realistic images. While plenty of works attempt to extend the unconditional generative models and achieve some level of controllability, it is still challenging to ensure multi-view consistency, especially in large poses. In this work, we propose a 3D portrait generation network that produces 3D consistent portraits while being controllable according to semantic parameters regarding pose, identity, expression and lighting. The generative network uses neural scene representation to model portraits in 3D, whose generation is guided by a parametric face model that supports explicit control. While the latent disentanglement can be further enhanced by contrasting images with partially different attributes, there still exists noticeable inconsistency in non-face areas, e.g., hair and background, when animating expressions. We solve this by proposing a volume blending strategy in which we form a composite output by blending the dynamic and static radiance fields, with two parts segmented from the jointly learned semantic field. Our method outperforms prior arts in extensive experiments, producing realistic portraits with vivid expression in natural lighting when viewed in free viewpoint. The proposed method also demonstrates generalization ability to real images as well as out-of-domain cartoon faces, showing great promise in real applications. Additional video results and code will be available on the project webpage.
PDF Project webpage: https://junshutang.github.io/control/index.html
点此查看论文截图