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。

Google Research Basecolor Metallic Roughness Normal Multi-View Images NeRD Volume Decomposed BRDF Relighting & View synthesis Textured MeshFigure 1: Neural Reflectance Decomposition for Relighting. We encode multiple views of an object under varying or fixed illumination into the NeRD volume.We decompose each given image into geometry, spatially-varying BRDF parameters and a rough approximation of the incident illumination in a globally consistent manner. We then extract a relightable textured mesh that can be re-rendered under novel illumination conditions in real-time.

我们将神经渲染与多模态图像和文本表示相结合，以仅从自然语言描述中综合不同的3D对象。我们的方法，梦场，可以产生多种物体的几何和颜色而无需3D监控。由于不同，标题3D数据的稀缺性，先前的方法仅生成来自少数类别的对象，例如ShapEnet。相反，我们指导生成与从Web的标题图像的大型数据集预先培训的图像文本模型。我们的方法优化了许多相机视图的神经辐射场，使得根据预先训练的剪辑模型，渲染图像非常高度地使用目标字幕。为了提高保真度和视觉质量，我们引入简单的几何前瞻，包括突出透射率正则化，场景界限和新的MLP架构。在实验中，梦场从各种自然语言标题中产生现实，多视图一致的物体几何和颜色。

Neural Radiance Fields (NeRFs) encode the radiance in a scene parameterized by the scene's plenoptic function. This is achieved by using an MLP together with a mapping to a higher-dimensional space, and has been proven to capture scenes with a great level of detail. Naturally, the same parameterization can be used to encode additional properties of the scene, beyond just its radiance. A particularly interesting property in this regard is the semantic decomposition of the scene. We introduce a novel technique for semantic soft decomposition of neural radiance fields (named SSDNeRF) which jointly encodes semantic signals in combination with radiance signals of a scene. Our approach provides a soft decomposition of the scene into semantic parts, enabling us to correctly encode multiple semantic classes blending along the same direction -- an impossible feat for existing methods. Not only does this lead to a detailed, 3D semantic representation of the scene, but we also show that the regularizing effects of the MLP used for encoding help to improve the semantic representation. We show state-of-the-art segmentation and reconstruction results on a dataset of common objects and demonstrate how the proposed approach can be applied for high quality temporally consistent video editing and re-compositing on a dataset of casually captured selfie videos.

我们提出了一种新的方法来获取来自在线图像集合的对象表示，从具有不同摄像机，照明和背景的照片捕获任意物体的高质量几何形状和材料属性。这使得各种以各种对象渲染应用诸如新颖的综合，致密和协调的背景组合物，从疯狂的内部输入。使用多级方法延伸神经辐射场，首先推断表面几何形状并优化粗估计的初始相机参数，同时利用粗糙的前景对象掩模来提高训练效率和几何质量。我们还介绍了一种强大的正常估计技术，其消除了几何噪声的效果，同时保持了重要细节。最后，我们提取表面材料特性和环境照明，以球形谐波表示，具有处理瞬态元素的延伸部，例如，锋利的阴影。这些组件的结合导致高度模块化和有效的对象采集框架。广泛的评估和比较证明了我们在捕获高质量的几何形状和外观特性方面的方法，可用于渲染应用。

综合照片 - 现实图像和视频是计算机图形的核心，并且是几十年的研究焦点。传统上，使用渲染算法（如光栅化或射线跟踪）生成场景的合成图像，其将几何形状和材料属性的表示为输入。统称，这些输入定义了实际场景和呈现的内容，并且被称为场景表示（其中场景由一个或多个对象组成）。示例场景表示是具有附带纹理的三角形网格（例如，由艺术家创建），点云（例如，来自深度传感器），体积网格（例如，来自CT扫描）或隐式曲面函数（例如，截短的符号距离）字段）。使用可分辨率渲染损耗的观察结果的这种场景表示的重建被称为逆图形或反向渲染。神经渲染密切相关，并将思想与经典计算机图形和机器学习中的思想相结合，以创建用于合成来自真实观察图像的图像的算法。神经渲染是朝向合成照片现实图像和视频内容的目标的跨越。近年来，我们通过数百个出版物显示了这一领域的巨大进展，这些出版物显示了将被动组件注入渲染管道的不同方式。这种最先进的神经渲染进步的报告侧重于将经典渲染原则与学习的3D场景表示结合的方法，通常现在被称为神经场景表示。这些方法的一个关键优势在于它们是通过设计的3D-一致，使诸如新颖的视点合成捕获场景的应用。除了处理静态场景的方法外，我们还涵盖了用于建模非刚性变形对象的神经场景表示...

神经隐式表示在新的视图合成和来自多视图图像的高质量3D重建方面显示了其有效性。但是，大多数方法都集中在整体场景表示上，但忽略了其中的各个对象，从而限制了潜在的下游应用程序。为了学习对象组合表示形式，一些作品将2D语义图作为训练中的提示，以掌握对象之间的差异。但是他们忽略了对象几何和实例语义信息之间的牢固联系，这导致了单个实例的不准确建模。本文提出了一个新颖的框架ObjectsDF，以在3D重建和对象表示中构建具有高保真度的对象复合神经隐式表示。观察常规音量渲染管道的歧义，我们通过组合单个对象的签名距离函数（SDF）来对场景进行建模，以发挥明确的表面约束。区分不同实例的关键是重新审视单个对象的SDF和语义标签之间的牢固关联。特别是，我们将语义信息转换为对象SDF的函数，并为场景和对象开发统一而紧凑的表示形式。实验结果表明，ObjectSDF框架在表示整体对象组合场景和各个实例方面的优越性。可以在https://qianyiwu.github.io/objectsdf/上找到代码

Neural implicit 3D representations have emerged as a powerful paradigm for reconstructing surfaces from multiview images and synthesizing novel views. Unfortunately, existing methods such as DVR or IDR require accurate perpixel object masks as supervision. At the same time, neural radiance fields have revolutionized novel view synthesis. However, NeRF's estimated volume density does not admit accurate surface reconstruction. Our key insight is that implicit surface models and radiance fields can be formulated in a unified way, enabling both surface and volume rendering using the same model. This unified perspective enables novel, more efficient sampling procedures and the ability to reconstruct accurate surfaces without input masks. We compare our method on the DTU, BlendedMVS, and a synthetic indoor dataset. Our experiments demonstrate that we outperform NeRF in terms of reconstruction quality while performing on par with IDR without requiring masks.

We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene using a fully-connected (nonconvolutional) deep network, whose input is a single continuous 5D coordinate (spatial location (x, y, z) and viewing direction (θ, φ)) and whose output is the volume density and view-dependent emitted radiance at that spatial location. We synthesize views by querying 5D coordinates along camera rays and use classic volume rendering techniques to project the output colors and densities into an image. Because volume rendering is naturally differentiable, the only input required to optimize our representation is a set of images with known camera poses. We describe how to effectively optimize neural radiance fields to render photorealistic novel views of scenes with complicated geometry and appearance, and demonstrate results that outperform prior work on neural rendering and view synthesis. View synthesis results are best viewed as videos, so we urge readers to view our supplementary video for convincing comparisons.

We present a method that takes as input a set of images of a scene illuminated by unconstrained known lighting, and produces as output a 3D representation that can be rendered from novel viewpoints under arbitrary lighting conditions. Our method represents the scene as a continuous volumetric function parameterized as MLPs whose inputs are a 3D location and whose outputs are the following scene properties at that input location: volume density, surface normal, material parameters, distance to the first surface intersection in any direction, and visibility of the external environment in any direction. Together, these allow us to render novel views of the object under arbitrary lighting, including indirect illumination effects. The predicted visibility and surface intersection fields are critical to our model's ability to simulate direct and indirect illumination during training, because the brute-force techniques used by prior work are intractable for lighting conditions outside of controlled setups with a single light. Our method outperforms alternative approaches for recovering relightable 3D scene representations, and performs well in complex lighting settings that have posed a significant challenge to prior work.

Input: 3 views of held-out scene NeRF pixelNeRF Output: Rendered new views Input Novel views Input Novel views Input Novel views Figure 1: NeRF from one or few images. We present pixelNeRF, a learning framework that predicts a Neural Radiance Field (NeRF) representation from a single (top) or few posed images (bottom). PixelNeRF can be trained on a set of multi-view images, allowing it to generate plausible novel view synthesis from very few input images without test-time optimization (bottom left). In contrast, NeRF has no generalization capabilities and performs poorly when only three input views are available (bottom right).

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.

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.

我们建议使用以光源方向为条件的神经辐射场（NERF）的扩展来解决多视光度立体声问题。我们神经表示的几何部分预测表面正常方向，使我们能够理解局部表面反射率。我们的神经表示的外观部分被分解为神经双向反射率函数（BRDF），作为拟合过程的一部分学习，阴影预测网络（以光源方向为条件），使我们能够对明显的BRDF进行建模。基于物理图像形成模型的诱导偏差的学到的组件平衡使我们能够远离训练期间观察到的光源和查看器方向。我们证明了我们在多视光学立体基准基准上的方法，并表明可以通过NERF的神经密度表示可以获得竞争性能。

We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on Neural Radiance Fields (NeRF), which uses the weights of a multilayer perceptron to model the density and color of a scene as a function of 3D coordinates. While NeRF works well on images of static subjects captured under controlled settings, it is incapable of modeling many ubiquitous, real-world phenomena in uncontrolled images, such as variable illumination or transient occluders. We introduce a series of extensions to NeRF to address these issues, thereby enabling accurate reconstructions from unstructured image collections taken from the internet. We apply our system, dubbed NeRF-W, to internet photo collections of famous landmarks, and demonstrate temporally consistent novel view renderings that are significantly closer to photorealism than the prior state of the art.

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

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.

在本文中，我们为复杂场景进行了高效且强大的深度学习解决方案。在我们的方法中，3D场景表示为光场，即，一组光线，每组在到达图像平面时具有相应的颜色。对于高效的新颖视图渲染，我们采用了光场的双面参数化，其中每个光线的特征在于4D参数。然后，我们将光场配向作为4D函数，即将4D坐标映射到相应的颜色值。我们训练一个深度完全连接的网络以优化这种隐式功能并记住3D场景。然后，特定于场景的模型用于综合新颖视图。与以前需要密集的视野的方法不同，需要密集的视野采样来可靠地呈现新颖的视图，我们的方法可以通过采样光线来呈现新颖的视图并直接从网络查询每种光线的颜色，从而使高质量的灯场呈现稀疏集合训练图像。网络可以可选地预测每光深度，从而使诸如自动重新焦点的应用。我们的小说视图合成结果与最先进的综合结果相当，甚至在一些具有折射和反射的具有挑战性的场景中优越。我们在保持交互式帧速率和小的内存占地面积的同时实现这一点。

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.

由于其成功在从稀疏的输入图像集合中合成了场景的新颖视图，最近越来越受欢迎。到目前为止，通过通用密度函数建模了神经体积渲染技术的几何形状。此外，使用通向嘈杂的任意水平函数的任意水平集合来提取几何形状本身，通常是低保真重建。本文的目标是改善神经体积渲染中的几何形象和重建。我们通过将体积密度建模为几何形状来实现这一点。这与以前的工作与体积密度的函数建模几何。更详细地，我们将音量密度函数定义为Laplace的累积分发功能（CDF）应用于符号距离功能（SDF）表示。这种简单的密度表示有三个好处：（i）它为神经体积渲染过程中学到的几何形状提供了有用的电感偏差; （ii）它促进了缺陷近似误差的束缚，导致观看光线的准确采样。精确的采样对于提供几何和光线的精确耦合非常重要; （iii）允许高效无监督的脱位形状和外观在体积渲染中。将此新密度表示应用于具有挑战性的场景多视图数据集生产了高质量的几何重建，表现优于相关的基线。此外，由于两者的解剖学，场景之间的切换形状和外观是可能的。