本文旨在减少透明辐射场的渲染时间。一些最近的作品用图像编码器配备了神经辐射字段，能够跨越场景概括，这避免了每场景优化。但是，它们的渲染过程通常很慢。主要因素是，在推断辐射场时，它们在空间中的大量点。在本文中，我们介绍了一个混合场景表示，它结合了最佳的隐式辐射场和显式深度映射，以便有效渲染。具体地，我们首先构建级联成本量，以有效地预测场景的粗糙几何形状。粗糙几何允许我们在场景表面附近的几个点来样，并显着提高渲染速度。该过程是完全可疑的，使我们能够仅从RGB图像共同学习深度预测和辐射现场网络。实验表明，该方法在DTU，真正的前瞻性和NERF合成数据集上展示了最先进的性能，而不是比以前的最可推广的辐射现场方法快至少50倍。我们还展示了我们的方法实时综合动态人类执行者的自由观点视频。代码将在https://zju3dv.github.io/enerf/处提供。

我们提出了HRF-NET，这是一种基于整体辐射场的新型视图合成方法，该方法使用一组稀疏输入来呈现新视图。最近的概括视图合成方法还利用了光辉场，但渲染速度不是实时的。现有的方法可以有效地训练和呈现新颖的观点，但它们无法概括地看不到场景。我们的方法解决了用于概括视图合成的实时渲染问题，并由两个主要阶段组成：整体辐射场预测指标和基于卷积的神经渲染器。该架构不仅基于隐式神经场的一致场景几何形状，而且还可以使用单个GPU有效地呈现新视图。我们首先在DTU数据集的多个3D场景上训练HRF-NET，并且网络只能仅使用光度损耗就看不见的真实和合成数据产生合理的新视图。此外，我们的方法可以利用单个场景的密集参考图像集来产生准确的新颖视图，而无需依赖其他明确表示，并且仍然保持了预训练模型的高速渲染。实验结果表明，HRF-NET优于各种合成和真实数据集的最先进的神经渲染方法。

We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates radiance and volume density at continuous 5D locations (3D spatial locations and 2D viewing directions), drawing appearance information on the fly from multiple source views. By drawing on source views at render time, our method hearkens back to classic work on image-based rendering (IBR), and allows us to render high-resolution imagery. Unlike neural scene representation work that optimizes per-scene functions for rendering, we learn a generic view interpolation function that generalizes to novel scenes. We render images using classic volume rendering, which is fully differentiable and allows us to train using only multiview posed images as supervision. Experiments show that our method outperforms recent novel view synthesis methods that also seek to generalize to novel scenes. Further, if fine-tuned on each scene, our method is competitive with state-of-the-art single-scene neural rendering methods. 1

我们呈现Geonerf，一种基于神经辐射场的完全光电素质性新颖性研究综合方法。我们的方法由两个主要阶段组成：几何推理和渲染器。为了渲染新颖的视图，几何件推理首先为每个附近的源视图构造级联成本卷。然后，使用基于变压器的注意力机制和级联成本卷，渲染器Infers的几何和外观，并通过经典音量渲染技术呈现细节的图像。特别是该架构允许复杂的遮挡推理，从一致的源视图中收集信息。此外，我们的方法可以在单个场景中轻松进行微调，通过每场比较优化的神经渲染方法呈现竞争结果，其数量是计算成本。实验表明，Geonerf优于各种合成和实时数据集的最先进的最新神经渲染模型。最后，随着对几何推理的略微修改，我们还提出了一种适应RGBD图像的替代模型。由于深度传感器，该模型通常直接利用经常使用的深度信息。实施代码将公开可用。

Volumetric neural rendering methods like NeRF generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time. On the other hand, deep multi-view stereo methods can quickly reconstruct scene geometry via direct network inference. Point-NeRF combines the advantages of these two approaches by using neural 3D point clouds, with associated neural features, to model a radiance field. Point-NeRF can be rendered efficiently by aggregating neural point features near scene surfaces, in a ray marching-based rendering pipeline. Moreover, Point-NeRF can be initialized via direct inference of a pre-trained deep network to produce a neural point cloud; this point cloud can be finetuned to surpass the visual quality of NeRF with 30X faster training time. Point-NeRF can be combined with other 3D reconstruction methods and handles the errors and outliers in such methods via a novel pruning and growing mechanism. The experiments on the DTU, the NeRF Synthetics , the ScanNet and the Tanks and Temples datasets demonstrate Point-NeRF can surpass the existing methods and achieve the state-of-the-art results.

b) MVS-NeRF no fine-tuning c) MVS-NeRF 6 min fine-tuning d) NeRF 5.1h optimization a) Source views SSIM:0.766 SSIM: 0.923 SSIM:0.924 * Equal contribution Research done when Anpei Chen was in a remote internship with UCSD.generalizable radiance field reconstruction. Moreover, if dense images are captured, our estimated radiance field representation can be easily fine-tuned; this leads to fast per-scene reconstruction with higher rendering quality and substantially less optimization time than NeRF.

Neural Radiance Field (NeRF) has revolutionized free viewpoint rendering tasks and achieved impressive results. However, the efficiency and accuracy problems hinder its wide applications. To address these issues, we propose Geometry-Aware Generalized Neural Radiance Field (GARF) with a geometry-aware dynamic sampling (GADS) strategy to perform real-time novel view rendering and unsupervised depth estimation on unseen scenes without per-scene optimization. Distinct from most existing generalized NeRFs, our framework infers the unseen scenes on both pixel-scale and geometry-scale with only a few input images. More specifically, our method learns common attributes of novel-view synthesis by an encoder-decoder structure and a point-level learnable multi-view feature fusion module which helps avoid occlusion. To preserve scene characteristics in the generalized model, we introduce an unsupervised depth estimation module to derive the coarse geometry, narrow down the ray sampling interval to proximity space of the estimated surface and sample in expectation maximum position, constituting Geometry-Aware Dynamic Sampling strategy (GADS). Moreover, we introduce a Multi-level Semantic Consistency loss (MSC) to assist more informative representation learning. Extensive experiments on indoor and outdoor datasets show that comparing with state-of-the-art generalized NeRF methods, GARF reduces samples by more than 25\%, while improving rendering quality and 3D geometry estimation.

最近，神经辐射场（NERF）正在彻底改变新型视图合成（NVS）的卓越性能。但是，NERF及其变体通常需要进行冗长的每场训练程序，其中将多层感知器（MLP）拟合到捕获的图像中。为了解决挑战，已经提出了体素网格表示，以显着加快训练的速度。但是，这些现有方法只能处理静态场景。如何开发有效，准确的动态视图合成方法仍然是一个开放的问题。将静态场景的方法扩展到动态场景并不简单，因为场景几何形状和外观随时间变化。在本文中，基于素素网格优化的最新进展，我们提出了一种快速变形的辐射场方法来处理动态场景。我们的方法由两个模块组成。第一个模块采用变形网格来存储3D动态功能，以及使用插值功能将观测空间中的3D点映射到规范空间的变形的轻巧MLP。第二个模块包含密度和颜色网格，以建模场景的几何形状和密度。明确对阻塞进行了建模，以进一步提高渲染质量。实验结果表明，我们的方法仅使用20分钟的训练就可以实现与D-NERF相当的性能，该训练比D-NERF快70倍以上，这清楚地证明了我们提出的方法的效率。

最近的神经人类表示可以产生高质量的多视图渲染，但需要使用密集的多视图输入和昂贵的培训。因此，它们在很大程度上仅限于静态模型，因为每个帧都是不可行的。我们展示了人类学 - 一种普遍的神经表示 - 用于高保真自由观察动态人类的合成。类似于IBRNET如何通过避免每场景训练来帮助NERF，Humannerf跨多视图输入采用聚合像素对准特征，以及用于解决动态运动的姿势嵌入的非刚性变形场。原始人物员已经可以在稀疏视频输入的稀疏视频输入上产生合理的渲染。为了进一步提高渲染质量，我们使用外观混合模块增强了我们的解决方案，用于组合神经体积渲染和神经纹理混合的益处。各种多视图动态人类数据集的广泛实验证明了我们在挑战运动中合成照片 - 现实自由观点的方法和非常稀疏的相机视图输入中的普遍性和有效性。

我们提出了一种可区分的渲染算法，以进行有效的新型视图合成。通过偏离基于音量的表示，支持学习点表示，我们在训练和推理方面的内存和运行时范围内改进了现有方法的数量级。该方法从均匀采样的随机点云开始，并使用基于可区分的SPLAT渲染器来发展模型以匹配一组输入图像，从而学习了每点位置和观看依赖性外观。在训练和推理中，我们的方法比NERF快300倍，质量只有边缘牺牲，而在静态场景中使用少于10 〜MB的记忆。对于动态场景，我们的方法比Stnerf训练两个数量级，并以接近互动速率渲染，同时即使在不施加任何时间固定的正则化合物的情况下保持较高的图像质量和时间连贯性。

Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have demonstrated promising results by learning scene representations that implicitly encode both geometry and appearance without 3D supervision. However, existing approaches in practice often show blurry renderings caused by the limited network capacity or the difficulty in finding accurate intersections of camera rays with the scene geometry. Synthesizing high-resolution imagery from these representations often requires time-consuming optical ray marching. In this work, we introduce Neural Sparse Voxel Fields (NSVF), a new neural scene representation for fast and high-quality free-viewpoint rendering. NSVF defines a set of voxel-bounded implicit fields organized in a sparse voxel octree to model local properties in each cell. We progressively learn the underlying voxel structures with a diffentiable ray-marching operation from only a set of posed RGB images. With the sparse voxel octree structure, rendering novel views can be accelerated by skipping the voxels containing no relevant scene content. Our method is typically over 10 times faster than the state-of-the-art (namely, NeRF (Mildenhall et al., 2020)) at inference time while achieving higher quality results. Furthermore, by utilizing an explicit sparse voxel representation, our method can easily be applied to scene editing and scene composition. We also demonstrate several challenging tasks, including multi-scene learning, free-viewpoint rendering of a moving human, and large-scale scene rendering. Code and data are available at our website: https://github.com/facebookresearch/NSVF.

我们探索了基于神经光场表示的几种新颖观点合成的新策略。给定目标摄像头姿势，隐式神经网络将每个射线映射到其目标像素的颜色。该网络的条件是根据来自显式3D特征量的粗量渲染产生的本地射线特征。该卷是由使用3D Convnet的输入图像构建的。我们的方法在基于最先进的神经辐射场竞争方面，在合成和真实MVS数据上实现了竞争性能，同时提供了100倍的渲染速度。

3D reconstruction and novel view synthesis of dynamic scenes from collections of single views recently gained increased attention. Existing work shows impressive results for synthetic setups and forward-facing real-world data, but is severely limited in the training speed and angular range for generating novel views. This paper addresses these limitations and proposes a new method for full 360{\deg} novel view synthesis of non-rigidly deforming scenes. At the core of our method are: 1) An efficient deformation module that decouples the processing of spatial and temporal information for acceleration at training and inference time; and 2) A static module representing the canonical scene as a fast hash-encoded neural radiance field. We evaluate the proposed approach on the established synthetic D-NeRF benchmark, that enables efficient reconstruction from a single monocular view per time-frame randomly sampled from a full hemisphere. We refer to this form of inputs as monocularized data. To prove its practicality for real-world scenarios, we recorded twelve challenging sequences with human actors by sampling single frames from a synchronized multi-view rig. In both cases, our method is trained significantly faster than previous methods (minutes instead of days) while achieving higher visual accuracy for generated novel views. Our source code and data is available at our project page https://graphics.tu-bs.de/publications/kappel2022fast.

Figure 1: Our method can synthesize novel views in both space and time from a single monocular video of a dynamic scene. Here we show video results with various configurations of fixing and interpolating view and time (left), as well as a visualization of the recovered scene geometry (right). Please view with Adobe Acrobat or KDE Okular to see animations.

Figure 1. Given a monocular image sequence, NR-NeRF reconstructs a single canonical neural radiance field to represent geometry and appearance, and a per-time-step deformation field. We can render the scene into a novel spatio-temporal camera trajectory that significantly differs from the input trajectory. NR-NeRF also learns rigidity scores and correspondences without direct supervision on either. We can use the rigidity scores to remove the foreground, we can supersample along the time dimension, and we can exaggerate or dampen motion.

本文解决了从多视频视频中重建动画人类模型的挑战。最近的一些作品提出，将一个非刚性变形的场景分解为规范的神经辐射场和一组变形场，它们映射观察空间指向规范空间，从而使它们能够从图像中学习动态场景。但是，它们代表变形场作为转换矢量场或SE（3）字段，这使得优化高度不受限制。此外，这些表示无法通过输入动议明确控制。取而代之的是，我们基于线性混合剥皮算法引入了一个姿势驱动的变形场，该算法结合了混合重量场和3D人类骨架，以产生观察到的对应对应。由于3D人类骨骼更容易观察到，因此它们可以正规化变形场的学习。此外，可以通过输入骨骼运动来控制姿势驱动的变形场，以生成新的变形字段来动画规范人类模型。实验表明，我们的方法显着优于最近的人类建模方法。该代码可在https://zju3dv.github.io/animatable_nerf/上获得。

Recent methods for neural surface representation and rendering, for example NeuS, have demonstrated remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8 hours), which makes it almost impossible to apply them to dynamic scenes with thousands of frames. We propose a fast neural surface reconstruction approach, called NeuS2, which achieves two orders of magnitude improvement in terms of acceleration without compromising reconstruction quality. To accelerate the training process, we integrate multi-resolution hash encodings into a neural surface representation and implement our whole algorithm in CUDA. We also present a lightweight calculation of second-order derivatives tailored to our networks (i.e., ReLU-based MLPs), which achieves a factor two speed up. To further stabilize training, a progressive learning strategy is proposed to optimize multi-resolution hash encodings from coarse to fine. In addition, we extend our method for reconstructing dynamic scenes with an incremental training strategy. Our experiments on various datasets demonstrate that NeuS2 significantly outperforms the state-of-the-arts in both surface reconstruction accuracy and training speed. The video is available at https://vcai.mpi-inf.mpg.de/projects/NeuS2/ .

Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virtual experiences is view synthesis of dynamic scenes. However, several challenges exist due to the lack of high-quality training datasets, and the additional time dimension for videos of dynamic scenes. To address this issue, we introduce a multi-view video dataset, captured with a custom 10-camera rig in 120FPS. The dataset contains 96 high-quality scenes showing various visual effects and human interactions in outdoor scenes. We develop a new algorithm, Deep 3D Mask Volume, which enables temporally-stable view extrapolation from binocular videos of dynamic scenes, captured by static cameras. Our algorithm addresses the temporal inconsistency of disocclusions by identifying the error-prone areas with a 3D mask volume, and replaces them with static background observed throughout the video. Our method enables manipulation in 3D space as opposed to simple 2D masks, We demonstrate better temporal stability than frame-by-frame static view synthesis methods, or those that use 2D masks. The resulting view synthesis videos show minimal flickering artifacts and allow for larger translational movements.

Neural Radiance Fields (NeRF) have demonstrated superior novel view synthesis performance but are slow at rendering. To speed up the volume rendering process, many acceleration methods have been proposed at the cost of large memory consumption. To push the frontier of the efficiency-memory trade-off, we explore a new perspective to accelerate NeRF rendering, leveraging a key fact that the viewpoint change is usually smooth and continuous in interactive viewpoint control. This allows us to leverage the information of preceding viewpoints to reduce the number of rendered pixels as well as the number of sampled points along the ray of the remaining pixels. In our pipeline, a low-resolution feature map is rendered first by volume rendering, then a lightweight 2D neural renderer is applied to generate the output image at target resolution leveraging the features of preceding and current frames. We show that the proposed method can achieve competitive rendering quality while reducing the rendering time with little memory overhead, enabling 30FPS at 1080P image resolution with a low memory footprint.

最近，我们看到了照片真实的人类建模和渲染的神经进展取得的巨大进展。但是，将它们集成到现有的下游应用程序中的现有网络管道中仍然具有挑战性。在本文中，我们提出了一种全面的神经方法，用于从密集的多视频视频中对人类表演进行高质量重建，压缩和渲染。我们的核心直觉是用一系列高效的神经技术桥接传统的动画网格工作流程。我们首先引入一个神经表面重建器，以在几分钟内进行高质量的表面产生。它与多分辨率哈希编码的截短签名距离场（TSDF）的隐式体积渲染相结合。我们进一步提出了一个混合神经跟踪器来生成动画网格，该网格将明确的非刚性跟踪与自我监督框架中的隐式动态变形结合在一起。前者将粗糙的翘曲返回到规范空间中，而后者隐含的一个隐含物进一步预测了使用4D哈希编码的位移，如我们的重建器中。然后，我们使用获得的动画网格讨论渲染方案，从动态纹理到各种带宽设置下的Lumigraph渲染。为了在质量和带宽之间取得复杂的平衡，我们通过首先渲染6个虚拟视图来涵盖表演者，然后进行闭塞感知的神经纹理融合，提出一个分层解决方案。我们证明了我们方法在各种平台上的各种基于网格的应用程序和照片真实的自由观看体验中的功效，即，通过移动AR插入虚拟人类的表演，或通过移动AR插入真实环境，或带有VR头戴式的人才表演。