我们介绍了Fadiv-Syn，一种快速深入的新型观点合成方法。相关方法通常受到它们的深度估计阶段的限制，其中不正确的深度预测可能导致大的投影误差。为避免此问题，我们将输入图像有效地将输入图像呈现为目标帧，以为一系列假定的深度平面。得到的平面扫描量（PSV）直接进入我们的网络，首先以自我监督的方式估计软PSV掩模，然后直接产生新颖的输出视图。因此，我们侧行显式深度估计。这提高了透明，反光，薄，特色场景部件上的效率和性能。 Fadiv-syn可以在大规模Realestate10K数据集上执行插值和外推任务，优于最先进的外推方法。与可比方法相比，它由于其轻量级架构而实现了实时性能。我们彻底评估消融，例如去除软掩蔽网络，从更少的示例中培训以及更高的分辨率和更强深度离散化的概括。

A recent strand of work in view synthesis uses deep learning to generate multiplane images-a camera-centric, layered 3D representation-given two or more input images at known viewpoints. We apply this representation to singleview view synthesis, a problem which is more challenging but has potentially much wider application. Our method learns to predict a multiplane image directly from a single image input, and we introduce scale-invariant view synthesis for supervision, enabling us to train on online video. We show this approach is applicable to several different datasets, that it additionally generates reasonable depth maps, and that it learns to fill in content behind the edges of foreground objects in background layers.Project page at https://single-view-mpi.github.io/.

用于运动中的人类的新型视图综合是一个具有挑战性的计算机视觉问题，使得诸如自由视视频之类的应用。现有方法通常使用具有多个输入视图，3D监控或预训练模型的复杂设置，这些模型不会概括为新标识。旨在解决这些限制，我们提出了一种新颖的视图综合框架，以从单视图传感器捕获的任何人的看法生成现实渲染，其具有稀疏的RGB-D，类似于低成本深度摄像头，而没有参与者特定的楷模。我们提出了一种架构来学习由基于球体的神经渲染获得的小说视图中的密集功能，并使用全局上下文修复模型创建完整的渲染。此外，增强剂网络利用了整体保真度，即使在原始视图中的遮挡区域中也能够产生细节的清晰渲染。我们展示了我们的方法为单个稀疏RGB-D输入产生高质量的合成和真实人体演员的新颖视图。它概括了看不见的身份，新的姿势，忠实地重建面部表情。我们的方法优于现有人体观测合成方法，并且对不同水平的输入稀疏性具有稳健性。

代表具有多个半透明彩色图层的场景是实时新型视图合成的流行和成功的选择。现有方法在平面或球形的规则间隔层上推断颜色和透明度值。在这项工作中，我们介绍了一种基于多个半透明层的新视图综合方法，具有场景适应的几何形状。我们的方法在两个阶段中介绍了立体对的这些表示。第一阶段从给定的一对视图中缩小了少数数据自适应层的几何形状。第二阶段为这些层的颜色和透明度值产生了新颖的视图合成的最终表示。重要的是，两个阶段都通过可差异化的渲染器连接，并以端到端的方式训练。在实验中，我们展示了所提出的方法在使用定期间隔的层上的优势，没有适应场景几何形状。尽管在渲染过程中较快的数量次数，但我们的方法也优于基于隐式几何表示的最近提出的IBRNET系统。查看https://samsunglabs.github.io/stereolayers的结果。

We present a method for novel view synthesis from input images that are freely distributed around a scene. Our method does not rely on a regular arrangement of input views, can synthesize images for free camera movement through the scene, and works for general scenes with unconstrained geometric layouts. We calibrate the input images via SfM and erect a coarse geometric scaffold via MVS. This scaffold is used to create a proxy depth map for a novel view of the scene. Based on this depth map, a recurrent encoder-decoder network processes reprojected features from nearby views and synthesizes the new view. Our network does not need to be optimized for a given scene. After training on a dataset, it works in previously unseen environments with no finetuning or per-scene optimization. We evaluate the presented approach on challenging real-world datasets, including Tanks and Temples, where we demonstrate successful view synthesis for the first time and substantially outperform prior and concurrent work.

虚拟现实（VR）耳机提供了一种身临其境的立体视觉体验，但以阻止用户直接观察其物理环境的代价。传递技术旨在通过利用向外的摄像头来重建否则没有耳机的用户可以看到的图像来解决此限制。这本质上是一个实时视图综合挑战，因为传递摄像机不能与眼睛进行物理共同。现有的通行技术会遭受分散重建工件的注意力，这主要是由于缺乏准确的深度信息（尤其是对于近场和分离的物体），并且表现出有限的图像质量（例如，低分辨率和单色）。在本文中，我们提出了第一种学习的传递方法，并使用包含立体声对RGB摄像机的自定义VR耳机评估其性能。通过模拟和实验，我们证明了我们所学的传递方法与最先进的方法相比提供了卓越的图像质量，同时满足了实时的，透视透视的立体视图综合的严格VR要求，从而在广泛的视野上综合用于桌面连接的耳机。

The DeepView architecture. (a) The network takes a sparse set of input images shot from different viewpoints. (b, c) The scene is reconstructed using learned gradient descent, producing a multi-plane image (a series of fronto-parallel, RGBA textured planes). (d)The multi-plane image is suitable for real-time, high-quality rendering of novel viewpoints. The result above uses four input views in a 30cm × 20cm rectangular layout. The novel view was rendered with a virtual camera positioned at the centroid of the four input views. More results, including video and an interactive viewer, at: https://augmentedperception.github.io/deepview/

Fast and easy handheld capture with guideline: closest object moves at most D pixels between views Promote sampled views to local light field via layered scene representation Blend neighboring local light fields to render novel views

现代计算机视觉已超越了互联网照片集的领域，并进入了物理世界，通过非结构化的环境引导配备摄像头的机器人和自动驾驶汽车。为了使这些体现的代理与现实世界对象相互作用，相机越来越多地用作深度传感器，重建了各种下游推理任务的环境。机器学习辅助的深度感知或深度估计会预测图像中每个像素的距离。尽管已经在深入估算中取得了令人印象深刻的进步，但仍然存在重大挑战：（1）地面真相深度标签很难大规模收集，（2）通常认为相机信息是已知的，但通常是不可靠的，并且（3）限制性摄像机假设很常见，即使在实践中使用了各种各样的相机类型和镜头。在本论文中，我们专注于放松这些假设，并描述将相机变成真正通用深度传感器的最终目标的贡献。

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。

新型视图合成（NVS）是一项具有挑战性的任务，需要系统从新观点中生成场景的影像图像，在新观点中，质量和速度对应用都很重要。以前的基于图像的渲染（IBR）方法很快，但是当输入视图稀疏时质量较差。最近的神经辐射场（NERF）和可推广的变体可带来令人印象深刻的结果，但不是实时的。在我们的论文中，我们提出了一种具有稀疏输入的可推广的NVS方法，称为FWD，该方法可实时提供高质量的合成。凭借明确的深度和可区分的渲染，它以130-1000 X的加速和更好的感知质量取得了SOTA方法的竞争结果。如果有的话，我们可以在训练或推理过程中无缝整合传感器深度，以提高图像质量，同时保持实时速度。随着深度传感器的越来越多的流行率，我们希望使用深度的方法将变得越来越有用。

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。

We explore the problem of view synthesis from a narrow baseline pair of images, and focus on generating highquality view extrapolations with plausible disocclusions. Our method builds upon prior work in predicting a multiplane image (MPI), which represents scene content as a set of RGBα planes within a reference view frustum and renders novel views by projecting this content into the target viewpoints. We present a theoretical analysis showing how the range of views that can be rendered from an MPI increases linearly with the MPI disparity sampling frequency, as well as a novel MPI prediction procedure that theoretically enables view extrapolations of up to 4× the lateral viewpoint movement allowed by prior work. Our method ameliorates two specific issues that limit the range of views renderable by prior methods: 1) We expand the range of novel views that can be rendered without depth discretization artifacts by using a 3D convolutional network architecture along with a randomized-resolution training procedure to allow our model to predict MPIs with increased disparity sampling frequency. 2) We reduce the repeated texture artifacts seen in disocclusions by enforcing a constraint that the appearance of hidden content at any depth must be drawn from visible content at or behind that depth.

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

新颖的视图合成（NVS）和视频预测（VP）通常被视为计算机视觉中的不相交任务。但是，它们都可以看作是观察空间时代世界的方法：NVS的目的是从新的角度综合一个场景，而副总裁则旨在从新的时间点观看场景。这两个任务提供了互补的信号以获得场景表示形式，因为观点从空间观察中变化为深度的变化，并且时间观察为相机和单个对象的运动提供了信息。受这些观察的启发，我们建议研究时空（背心）中视频外推的问题。我们提出了一个模型，该模型利用了两项任务的自学和互补线索，而现有方法只能解决其中之一。实验表明，我们的方法比室内和室外现实世界数据集上的几种最先进的NVS和VP方法更好地实现了性能。

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods.Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark.

Deep networks have recently enjoyed enormous success when applied to recognition and classification problems in computer vision [20,29], but their use in graphics problems has been limited ([21, 7] are notable recent exceptions). In this work, we present a novel deep architecture that performs new view synthesis directly from pixels, trained from a large number of posed image sets. In contrast to traditional approaches which consist of multiple complex stages of processing, each of which require careful tuning and can fail in unexpected ways, our system is trained end-to-end. The pixels from neighboring views of a scene are presented to the network which then directly produces the pixels of the unseen view. The benefits of our approach include generality (we only require posed image sets and can easily apply our method to different domains), and high quality results on traditionally difficult scenes. We believe this is due to the end-to-end nature of our system which is able to plausibly generate pixels according to color, depth, and texture priors learnt automatically from the training data. To verify our method we show that it can convincingly reproduce known test views from nearby imagery. Additionally we show images rendered from novel viewpoints. To our knowledge, our work is the first to apply deep learning to the problem of new view synthesis from sets of real-world, natural imagery.

我们介绍了与给定单个图像的任意长相机轨迹相对应的长期视图的新面积视图的问题。这是一个具有挑战性的问题，远远超出了当前视图合成方法的能力，这在提出大型摄像机运动时快速退化。用于视频生成的方法也具有有限的生产长序列的能力，并且通常不适用于场景几何形状。我们采用混合方法，它以迭代`\ emph {render}，\ emph {refine}，\ emph {重复}'框架集成了几何和图像合成，允许在数百帧之后覆盖大距离的远程生成。我们的方法可以从一组单目的视频序列训练。我们提出了一个沿海场景的空中镜头数据集，并比较了我们最近的观看综合和有条件的视频生成基线的方法，表明它可以在与现有方法相比，在大型相机轨迹上产生更长的时间范围。项目页面https://infinite-nature.github.io/。

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.