Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable with other people. Before sharing a NeRF, though, it might be desirable to remove personal information or unsightly objects. Such removal is not easily achieved with the current NeRF editing frameworks. We propose a framework to remove objects from a NeRF representation created from an RGB-D sequence. Our NeRF inpainting method leverages recent work in 2D image inpainting and is guided by a user-provided mask. Our algorithm is underpinned by a confidence based view selection procedure. It chooses which of the individual 2D inpainted images to use in the creation of the NeRF, so that the resulting inpainted NeRF is 3D consistent. We show that our method for NeRF editing is effective for synthesizing plausible inpaintings in a multi-view coherent manner. We validate our approach using a new and still-challenging dataset for the task of NeRF inpainting.

尽管神经辐射场（NERF）表现出引人注目的新视图综合结果，但编辑预训练的NERF仍然没有直觉，因为神经网络的参数和场景几何/外观通常没有明确关联。在本文中，我们介绍了第一个框架，该框架使用户能够在3D场景中删除不需要的对象或修饰不希望的区域，该场景由预先训练的NERF表示，而没有任何类别的数据和培训。用户首先绘制一个自由形式的掩码，以通过预先训练的NERF的渲染视图指定包含不需要对象的区域。我们的框架首先将用户提供的掩码转移到其他渲染视图，并估算这些传输的蒙版区域内的指导颜色和深度图像。接下来，我们制定了一个优化问题，该问题通过更新NERF模型的参数，共同对所有掩盖区域中的图像内容共同涂抹图像内容。我们在不同的场景上演示了我们的框架，并证明它在使用较短的时间和用户手动努力的情况下，在多个视图中获得了视觉上的合理和结构一致的结果。

神经辐射字段（NERF）将场景编码为神经表示，使得能够实现新颖视图的照片逼真。然而，RGB图像的成功重建需要在静态条件下拍摄的大量输入视图 - 通常可以为房间尺寸场景的几百个图像。我们的方法旨在将整个房间的小说视图从数量级的图像中合成。为此，我们利用密集的深度前导者来限制NERF优化。首先，我们利用从用于估计相机姿势的运动（SFM）预处理步骤的结构自由提供的稀疏深度数据。其次，我们使用深度完成将这些稀疏点转换为密集的深度图和不确定性估计，用于指导NERF优化。我们的方法使数据有效的新颖观看综合在挑战室内场景中，使用少量为整个场景的18张图像。

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.

我们提出了一种基于神经辐射场（NERF）的单个$ 360^\ PANORAMA图像合成新视图的方法。在类似环境中的先前研究依赖于多层感知的邻居插值能力来完成由遮挡引起的丢失区域，这导致其预测中的伪像。我们提出了360Fusionnerf，这是一个半监督的学习框架，我们介绍几何监督和语义一致性，以指导渐进式培训过程。首先，将输入图像重新投影至$ 360^\ Circ $图像，并在其他相机位置提取辅助深度图。除NERF颜色指导外，深度监督还改善了合成视图的几何形状。此外，我们引入了语义一致性损失，鼓励新观点的现实渲染。我们使用预先训练的视觉编码器（例如剪辑）提取这些语义功能，这是一个视觉变压器，经过数以千计的不同2D照片，并通过自然语言监督从网络中挖掘出来。实验表明，我们提出的方法可以在保留场景的特征的同时产生未观察到的区域的合理完成。 360fusionnerf在各种场景中接受培训时，转移到合成结构3D数据集（PSNR〜5％，SSIM〜3％lpips〜13％）时，始终达到最先进的性能，SSIM〜3％LPIPS〜9％）和replica360数据集（PSNR〜8％，SSIM〜2％LPIPS〜18％）。

对人类的逼真渲染和安息对于实现增强现实体验至关重要。我们提出了一个新颖的框架，以重建人类和场景，可以用新颖的人类姿势和景色从一个单一的野外视频中呈现。给定一个由移动摄像机捕获的视频，我们训练了两个NERF模型：人类NERF模型和一个场景NERF模型。为了训练这些模型，我们依靠现有方法来估计人类和场景的粗糙几何形状。这些粗糙的几何估计值使我们能够创建一个从观察空间到独立姿势独立的空间的翘曲场10秒的视频剪辑，并以新颖的观点以及背景提供新颖的姿势，提供人类的高质量效果。

https://video-nerf.github.io Figure 1. Our method takes a single casually captured video as input and learns a space-time neural irradiance field. (Top) Sample frames from the input video. (Middle) Novel view images rendered from textured meshes constructed from depth maps. (Bottom) Our results rendered from the proposed space-time neural irradiance field.

我们引入了一个可扩展的框架，用于从RGB-D图像中具有很大不完整的场景覆盖率的新型视图合成。尽管生成的神经方法在2D图像上表现出了惊人的结果，但它们尚未达到相似的影像学结果，并结合了场景完成，在这种情况下，空间3D场景的理解是必不可少的。为此，我们提出了一条在基于网格的神经场景表示上执行的生成管道，通过以2.5D-3D-2.5D方式进行场景的分布来完成未观察到的场景部分。我们在3D空间中处理编码的图像特征，并具有几何完整网络和随后的纹理镶嵌网络，以推断缺失区域。最终可以通过与一致性的可区分渲染获得感性图像序列。全面的实验表明，我们方法的图形输出优于最新技术，尤其是在未观察到的场景部分中。

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.

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.

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。

We address the problem of synthesizing novel views from a monocular video depicting a complex dynamic scene. State-of-the-art methods based on temporally varying Neural Radiance Fields (aka dynamic NeRFs) have shown impressive results on this task. However, for long videos with complex object motions and uncontrolled camera trajectories, these methods can produce blurry or inaccurate renderings, hampering their use in real-world applications. Instead of encoding the entire dynamic scene within the weights of an MLP, we present a new approach that addresses these limitations by adopting a volumetric image-based rendering framework that synthesizes new viewpoints by aggregating features from nearby views in a scene-motion-aware manner. Our system retains the advantages of prior methods in its ability to model complex scenes and view-dependent effects, but also enables synthesizing photo-realistic novel views from long videos featuring complex scene dynamics with unconstrained camera trajectories. We demonstrate significant improvements over state-of-the-art methods on dynamic scene datasets, and also apply our approach to in-the-wild videos with challenging camera and object motion, where prior methods fail to produce high-quality renderings. Our project webpage is at dynibar.github.io.

这项工作的目标是通过扫描平台捕获的数据进行3D重建和新颖的观看综合，该平台在城市室外环境中常设世界映射（例如，街景）。给定一系列由摄像机和扫描仪通过室外场景的摄像机和扫描仪进行的序列，我们产生可以从中提取3D表面的模型，并且可以合成新颖的RGB图像。我们的方法扩展了神经辐射字段，已经证明了用于在受控设置中的小型场景中的逼真新颖的图像，用于利用异步捕获的LIDAR数据，用于寻址捕获图像之间的曝光变化，以及利用预测的图像分段来监督密度。在光线指向天空。这三个扩展中的每一个都在街道视图数据上的实验中提供了显着的性能改进。我们的系统产生最先进的3D表面重建，并与传统方法（例如〜Colmap）和最近的神经表示（例如〜MIP-NERF）相比，合成更高质量的新颖视图。

获取3D对象表示对于创建照片现实的模拟器和为AR/VR应用程序收集资产很重要。神经领域已经显示出其在学习2D图像的场景的连续体积表示方面的有效性，但是从这些模型中获取对象表示，并以较弱的监督仍然是一个开放的挑战。在本文中，我们介绍了Laterf，一种从给定的2D图像和已知相机姿势的2D图像中提取感兴趣对象的方法，对象的自然语言描述以及少数对象和非对象标签 - 输入图像中的对象点。为了忠实地从场景中提取对象，后来在每个3D点上都以其他“对象”概率扩展NERF公式。此外，我们利用预先训练的剪辑模型与我们可区分的对象渲染器相结合的丰富潜在空间来注入对象的封闭部分。我们在合成数据集和真实数据集上展示了高保真对象提取，并通过广泛的消融研究证明我们的设计选择是合理的。

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.

Training a Neural Radiance Field (NeRF) without pre-computed camera poses is challenging. Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes. However, these methods still face difficulties during dramatic camera movement. We tackle this challenging problem by incorporating undistorted monocular depth priors. These priors are generated by correcting scale and shift parameters during training, with which we are then able to constrain the relative poses between consecutive frames. This constraint is achieved using our proposed novel loss functions. Experiments on real-world indoor and outdoor scenes show that our method can handle challenging camera trajectories and outperforms existing methods in terms of novel view rendering quality and pose estimation accuracy.

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.

我们介绍了神经点光场，它用稀疏点云上的轻场隐含地表示场景。结合可分辨率的体积渲染与学习的隐式密度表示使得可以合成用于小型场景的新颖视图的照片现实图像。作为神经体积渲染方法需要潜在的功能场景表示的浓密采样，在沿着射线穿过体积的数百个样本，它们从根本上限制在具有投影到数百个训练视图的相同对象的小场景。向神经隐式光线推广稀疏点云允许我们有效地表示每个光线的单个隐式采样操作。这些点光场作为光线方向和局部点特征邻域的函数，允许我们在没有密集的物体覆盖和视差的情况下插入光场条件训练图像。我们评估大型驾驶场景的新型视图综合的提出方法，在那里我们综合了现实的看法，即现有的隐式方法未能代表。我们验证了神经点光场可以通过显式建模场景来实现沿着先前轨迹的视频来预测沿着看不见的轨迹的视频。

神经场景表示，例如神经辐射场（NERF），基于训练多层感知器（MLP），使用一组具有已知姿势的彩色图像。现在，越来越多的设备产生RGB-D（颜色 +深度）信息，这对于各种任务非常重要。因此，本文的目的是通过将深度信息与颜色图像结合在一起，研究这些有希望的隐式表示可以进行哪些改进。特别是，最近建议的MIP-NERF方法使用圆锥形的圆丝而不是射线进行音量渲染，它使人们可以考虑具有距离距离摄像头中心距离的像素的不同区域。所提出的方法还模拟了深度不确定性。这允许解决基于NERF的方法的主要局限性，包括提高几何形状的准确性，减少伪像，更快的训练时间和缩短预测时间。实验是在众所周知的基准场景上进行的，并且比较在场景几何形状和光度重建中的准确性提高，同时将训练时间减少了3-5次。

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。