We present a unified and compact representation for object rendering, 3D reconstruction, and grasp pose prediction that can be inferred from a single image within a few seconds. We achieve this by leveraging recent advances in the Neural Radiance Field (NeRF) literature that learn category-level priors and fine-tune on novel objects with minimal data and time. Our insight is that we can learn a compact shape representation and extract meaningful additional information from it, such as grasping poses. We believe this to be the first work to retrieve grasping poses directly from a NeRF-based representation using a single viewpoint (RGB-only), rather than going through a secondary network and/or representation. When compared to prior art, our method is two to three orders of magnitude smaller while achieving comparable performance at view reconstruction and grasping. Accompanying our method, we also propose a new dataset of rendered shoes for training a sim-2-real NeRF method with grasping poses for different widths of grippers.

Neural Radiance Field (NeRF), a new novel view synthesis with implicit scene representation has taken the field of Computer Vision by storm. As a novel view synthesis and 3D reconstruction method, NeRF models find applications in robotics, urban mapping, autonomous navigation, virtual reality/augmented reality, and more. Since the original paper by Mildenhall et al., more than 250 preprints were published, with more than 100 eventually being accepted in tier one Computer Vision Conferences. Given NeRF popularity and the current interest in this research area, we believe it necessary to compile a comprehensive survey of NeRF papers from the past two years, which we organized into both architecture, and application based taxonomies. We also provide an introduction to the theory of NeRF based novel view synthesis, and a benchmark comparison of the performance and speed of key NeRF models. By creating this survey, we hope to introduce new researchers to NeRF, provide a helpful reference for influential works in this field, as well as motivate future research directions with our discussion section.

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).

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。

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...

我们提出了IM2NERF，这是一个学习框架，该框架可以预测在野生中给出单个输入图像的连续神经对象表示，仅通过现成的识别方法进行分割输出而受到监督。构建神经辐射场的标准方法利用了多视图的一致性，需要对场景的许多校准视图，这一要求在野外学习大规模图像数据时无法满足。我们通过引入一个模型将输入图像编码到包含对象形状的代码，对象外观代码以及捕获对象图像的估计相机姿势的模型来迈出解决此缺点的一步。我们的模型条件在预测的对象表示上nerf，并使用卷渲染来从新视图中生成图像。我们将模型端到端训练大量输入图像。由于该模型仅配有单视图像，因此问题高度不足。因此，除了在合成的输入视图上使用重建损失外，我们还对新颖的视图使用辅助对手损失。此外，我们利用对象对称性和循环摄像头的姿势一致性。我们在Shapenet数据集上进行了广泛的定量和定性实验，并在开放图像数据集上进行了定性实验。我们表明，在所有情况下，IM2NERF都从野外的单视图像中实现了新视图合成的最新性能。

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 introduce a method to render Neural Radiance Fields (NeRFs) in real time using PlenOctrees, an octree-based 3D representation which supports view-dependent effects. Our method can render 800×800 images at more than 150 FPS, which is over 3000 times faster than conventional NeRFs. We do so without sacrificing quality while preserving the ability of NeRFs to perform free-viewpoint rendering of scenes with arbitrary geometry and view-dependent effects. Real-time performance is achieved by pre-tabulating the NeRF into a PlenOctree. In order to preserve viewdependent effects such as specularities, we factorize the appearance via closed-form spherical basis functions. Specifically, we show that it is possible to train NeRFs to predict a spherical harmonic representation of radiance, removing the viewing direction as an input to the neural network. Furthermore, we show that PlenOctrees can be directly optimized to further minimize the reconstruction loss, which leads to equal or better quality compared to competing methods. Moreover, this octree optimization step can be used to reduce the training time, as we no longer need to wait for the NeRF training to converge fully. Our real-time neural rendering approach may potentially enable new applications such as 6-DOF industrial and product visualizations, as well as next generation AR/VR systems. PlenOctrees are amenable to in-browser rendering as well; please visit the project page for the interactive online demo, as well as video and code: https://alexyu. net/plenoctrees.

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。

机器学习的最近进步已经创造了利用一类基于坐标的神经网络来解决视觉计算问题的兴趣，该基于坐标的神经网络在空间和时间跨空间和时间的场景或对象的物理属性。我们称之为神经领域的这些方法已经看到在3D形状和图像的合成中成功应用，人体的动画，3D重建和姿势估计。然而，由于在短时间内的快速进展，许多论文存在，但尚未出现全面的审查和制定问题。在本报告中，我们通过提供上下文，数学接地和对神经领域的文学进行广泛综述来解决这一限制。本报告涉及两种维度的研究。在第一部分中，我们通过识别神经字段方法的公共组件，包括不同的表示，架构，前向映射和泛化方法来专注于神经字段的技术。在第二部分中，我们专注于神经领域的应用在视觉计算中的不同问题，超越（例如，机器人，音频）。我们的评论显示了历史上和当前化身的视觉计算中已覆盖的主题的广度，展示了神经字段方法所带来的提高的质量，灵活性和能力。最后，我们展示了一个伴随着贡献本综述的生活版本，可以由社区不断更新。

计算机愿景中的经典问题是推断从几个可用于以交互式速率渲染新颖视图的图像的3D场景表示。以前的工作侧重于重建预定定义的3D表示，例如，纹理网格或隐式表示，例如隐式表示。辐射字段，并且通常需要输入图像，具有精确的相机姿势和每个新颖场景的长处理时间。在这项工作中，我们提出了场景表示变换器（SRT），一种方法，该方法处理新的区域的构成或未铺设的RGB图像，Infers Infers“设置 - 潜在场景表示”，并合成新颖的视图，全部在一个前馈中经过。为了计算场景表示，我们提出了视觉变压器的概括到图像组，实现全局信息集成，从而实现3D推理。一个有效的解码器变压器通过参加场景表示来参加光场以呈现新颖的视图。通过最大限度地减少新型视图重建错误，学习是通过最终到底的。我们表明，此方法在PSNR和Synthetic DataSets上的速度方面优于最近的基线，包括为纸张创建的新数据集。此外，我们展示了使用街景图像支持现实世界户外环境的交互式可视化和语义分割。

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。

Humans form mental images of 3D scenes to support counterfactual imagination, planning, and motor control. Our abilities to predict the appearance and affordance of the scene from previously unobserved viewpoints aid us in performing manipulation tasks (e.g., 6-DoF kitting) with a level of ease that is currently out of reach for existing robot learning frameworks. In this work, we aim to build artificial systems that can analogously plan actions on top of imagined images. To this end, we introduce Mental Imagery for Robotic Affordances (MIRA), an action reasoning framework that optimizes actions with novel-view synthesis and affordance prediction in the loop. Given a set of 2D RGB images, MIRA builds a consistent 3D scene representation, through which we synthesize novel orthographic views amenable to pixel-wise affordances prediction for action optimization. We illustrate how this optimization process enables us to generalize to unseen out-of-plane rotations for 6-DoF robotic manipulation tasks given a limited number of demonstrations, paving the way toward machines that autonomously learn to understand the world around them for planning actions.

我们引入了来自多个机器人手的对象的神经隐式表示。多个机器人手之间的不同抓地力被编码为共享的潜在空间。学会了每个潜在矢量以两个3D形状的签名距离函数来解码对象的3D形状和机器人手的3D形状。此外，学会了潜在空间中的距离度量，以保留不同机器人手之间的graSps之间的相似性，其中根据机器人手的接触区域定义了grasps的相似性。该属性使我们能够在包括人手在内的不同抓地力之间转移抓地力，并且GRASP转移有可能在机器人之间分享抓地力，并使机器人能够从人类那里学习掌握技能。此外，我们隐式表示中对象和grasps的编码符号距离函数可用于6D对象姿势估计，并从部分点云中掌握触点优化，这可以在现实世界中启用机器人抓握。

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。

抓握是通过在一组触点上施加力和扭矩来挑选对象的过程。深度学习方法的最新进展允许在机器人对象抓地力方面快速进步。我们在过去十年中系统地调查了出版物，特别感兴趣使用最终效果姿势的所有6度自由度抓住对象。我们的综述发现了四种用于机器人抓钩的常见方法：基于抽样的方法，直接回归，强化学习和示例方法。此外，我们发现了围绕抓握的两种“支持方法”，这些方法使用深入学习来支持抓握过程，形状近似和负担能力。我们已经将本系统评论（85篇论文）中发现的出版物提炼为十个关键要点，我们认为对未来的机器人抓握和操纵研究至关重要。该调查的在线版本可从https://rhys-newbury.github.io/projects/6dof/获得

We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training. While NeRF is usually trained with ground-truth camera poses, multiple extensions have been proposed to reduce the need for this expensive supervision. Nonetheless, most of these methods still struggle in complex settings with large camera movements, and are restricted to single scenes, i.e. they cannot be trained on a collection of scenes depicting the same object category. To address these issues, our method uses an analysis by synthesis approach, combining a conditional NeRF with a viewpoint predictor and a scene encoder in order to produce self-supervised reconstructions for whole object categories. Rather than focusing on high fidelity reconstruction, we target efficient and accurate viewpoint prediction in complex scenarios, e.g. 360{\deg} rotation on real data. Our model shows competitive results on synthetic and real datasets, both for single scenes and multi-instance collections.

自从神经辐射场（NERF）出现以来，神经渲染引起了极大的关注，并且已经大大推动了新型视图合成的最新作品。最近的重点是在模型上过度适合单个场景，以及学习模型的一些尝试，这些模型可以综合看不见的场景的新型视图，主要包括将深度卷积特征与类似NERF的模型组合在一起。我们提出了一个不同的范式，不需要深层特征，也不需要类似NERF的体积渲染。我们的方法能够直接从现场采样的贴片集中直接预测目标射线的颜色。我们首先利用表现几何形状沿着每个参考视图的异性线提取斑块。每个贴片线性地投影到1D特征向量和一系列变压器处理集合中。对于位置编码，我们像在光场表示中一样对射线进行参数化，并且至关重要的差异是坐标是相对于目标射线的规范化的，这使我们的方法与参考帧无关并改善了概括。我们表明，即使接受比先前的工作要少得多的数据训练，我们的方法在新颖的综合综合方面都超出了最新的视图综合。

我们提出了一个基于变压器的NERF（Transnerf），以学习在新视图合成任务的观察视图图像上进行的通用神经辐射场。相比之下，现有的基于MLP的NERF无法直接接收具有任意号码的观察视图，并且需要基于辅助池的操作来融合源视图信息，从而导致源视图与目标渲染视图之间缺少复杂的关系。此外，当前方法分别处理每个3D点，忽略辐射场场景表示的局部一致性。这些局限性可能会在挑战现实世界应用中降低其性能，在这些应用程序中可能存在巨大的差异和新颖的渲染视图之间的巨大差异。为了应对这些挑战，我们的Transnerf利用注意机制自然地将任意数量的源视图的深层关联解码为基于坐标的场景表示。在统一变压器网络中，在射线铸造空间和周围视图空间中考虑了形状和外观的局部一致性。实验表明，与基于图像的最先进的基于图像的神经渲染方法相比，我们在各种场景上接受过培训的Transnf可以在场景 - 敏捷和每个场景的燃烧场景中获得更好的性能。源视图与渲染视图之间的差距很大。