2022-10-11 更新
Estimating Neural Reflectance Field from Radiance Field using Tree Structures
Authors:Xiu Li, Xiao Li, Yan Lu
We present a new method for estimating the Neural Reflectance Field (NReF) of an object from a set of posed multi-view images under unknown lighting. NReF represents 3D geometry and appearance of objects in a disentangled manner, and are hard to be estimated from images only. Our method solves this problem by exploiting the Neural Radiance Field (NeRF) as a proxy representation, from which we perform further decomposition. A high-quality NeRF decomposition relies on good geometry information extraction as well as good prior terms to properly resolve ambiguities between different components. To extract high-quality geometry information from radiance fields, we re-design a new ray-casting based method for surface point extraction. To efficiently compute and apply prior terms, we convert different prior terms into different type of filter operations on the surface extracted from radiance field. We then employ two type of auxiliary data structures, namely Gaussian KD-tree and octree, to support fast querying of surface points and efficient computation of surface filters during training. Based on this, we design a multi-stage decomposition optimization pipeline for estimating neural reflectance field from neural radiance fields. Extensive experiments show our method outperforms other state-of-the-art methods on different data, and enable high-quality free-view relighting as well as material editing tasks.
PDF
点此查看论文截图
Towards Efficient Neural Scene Graphs by Learning Consistency Fields
Authors:Yeji Song, Chaerin Kong, Seoyoung Lee, Nojun Kwak, Joonseok Lee
Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) \cite{ost2021neural} extends it to dynamic scenes (video) with multiple objects. Nevertheless, computationally heavy ray marching for every image frame becomes a huge burden. In this paper, taking advantage of significant redundancy across adjacent frames in videos, we propose a feature-reusing framework. From the first try of naively reusing the NSG features, however, we learn that it is crucial to disentangle object-intrinsic properties consistent across frames from transient ones. Our proposed method, \textit{Consistency-Field-based NSG (CF-NSG)}, reformulates neural radiance fields to additionally consider \textit{consistency fields}. With disentangled representations, CF-NSG takes full advantage of the feature-reusing scheme and performs an extended degree of scene manipulation in a more controllable manner. We empirically verify that CF-NSG greatly improves the inference efficiency by using 85\% less queries than NSG without notable degradation in rendering quality. Code will be available at: https://github.com/ldynx/CF-NSG
PDF BMVC 2022, 22 pages
点此查看论文截图
NerfAcc: A General NeRF Acceleration Toolbox
Authors:Ruilong Li, Matthew Tancik, Angjoo Kanazawa
We propose NerfAcc, a toolbox for efficient volumetric rendering of radiance fields. We build on the techniques proposed in Instant-NGP, and extend these techniques to not only support bounded static scenes, but also for dynamic scenes and unbounded scenes. NerfAcc comes with a user-friendly Python API, and is ready for plug-and-play acceleration of most NeRFs. Various examples are provided to show how to use this toolbox. Code can be found here: https://github.com/KAIR-BAIR/nerfacc.
PDF Webpage: https://www.nerfacc.com/
点此查看论文截图
EVA3D: Compositional 3D Human Generation from 2D Image Collections
Authors:Fangzhou Hong, Zhaoxi Chen, Yushi Lan, Liang Pan, Ziwei Liu
Inverse graphics aims to recover 3D models from 2D observations. Utilizing differentiable rendering, recent 3D-aware generative models have shown impressive results of rigid object generation using 2D images. However, it remains challenging to generate articulated objects, like human bodies, due to their complexity and diversity in poses and appearances. In this work, we propose, EVA3D, an unconditional 3D human generative model learned from 2D image collections only. EVA3D can sample 3D humans with detailed geometry and render high-quality images (up to 512x256) without bells and whistles (e.g. super resolution). At the core of EVA3D is a compositional human NeRF representation, which divides the human body into local parts. Each part is represented by an individual volume. This compositional representation enables 1) inherent human priors, 2) adaptive allocation of network parameters, 3) efficient training and rendering. Moreover, to accommodate for the characteristics of sparse 2D human image collections (e.g. imbalanced pose distribution), we propose a pose-guided sampling strategy for better GAN learning. Extensive experiments validate that EVA3D achieves state-of-the-art 3D human generation performance regarding both geometry and texture quality. Notably, EVA3D demonstrates great potential and scalability to “inverse-graphics” diverse human bodies with a clean framework.
PDF Project Page at https://hongfz16.github.io/projects/EVA3D.html
点此查看论文截图
Data augmentation for NeRF: a geometric consistent solution based on view morphing
Authors:Matteo Bortolon, Alessio Del Bue, Fabio Poiesi
NeRF aims to learn a continuous neural scene representation by using a finite set of input images taken from different viewpoints. The fewer the number of viewpoints, the higher the likelihood of overfitting on them. This paper mitigates such limitation by presenting a novel data augmentation approach to generate geometrically consistent image transitions between viewpoints using view morphing. View morphing is a highly versatile technique that does not requires any prior knowledge about the 3D scene because it is based on general principles of projective geometry. A key novelty of our method is to use the very same depths predicted by NeRF to generate the image transitions that are then added to NeRF training. We experimentally show that this procedure enables NeRF to improve the quality of its synthesised novel views in the case of datasets with few training viewpoints. We improve PSNR up to 1.8dB and 10.5dB when eight and four views are used for training, respectively. To the best of our knowledge, this is the first data augmentation strategy for NeRF that explicitly synthesises additional new input images to improve the model generalisation.
PDF
点此查看论文截图
SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction
Authors:Yitong Xia, Hao Tang, Radu Timofte, Luc Van Gool
NeRFmm is the Neural Radiance Fields (NeRF) that deal with Joint Optimization tasks, i.e., reconstructing real-world scenes and registering camera parameters simultaneously. Despite NeRFmm producing precise scene synthesis and pose estimations, it still struggles to outperform the full-annotated baseline on challenging scenes. In this work, we identify that there exists a systematic sub-optimality in joint optimization and further identify multiple potential sources for it. To diminish the impacts of potential sources, we propose Sinusoidal Neural Radiance Fields (SiNeRF) that leverage sinusoidal activations for radiance mapping and a novel Mixed Region Sampling (MRS) for selecting ray batch efficiently. Quantitative and qualitative results show that compared to NeRFmm, SiNeRF achieves comprehensive significant improvements in image synthesis quality and pose estimation accuracy. Codes are available at https://github.com/yitongx/sinerf.
PDF Accepted yet not published by BMVC2022
点此查看论文截图