我们介绍了一个自由视的渲染方法 - Humannerf - 这对人类进行了复杂的身体运动的给定单曲视频工作，例如，来自YouTube的视频。我们的方法可以在任何帧中暂停视频，并从任意新相机视点呈现对象，甚至是该特定帧和身体姿势的完整360度摄像机路径。这项任务特别具有挑战性，因为它需要合成身体的光电型细节，如从输入视频中可能不存在的各种相机角度所见，以及合成布折叠和面部外观的细细节。我们的方法优化了在规范T型姿势中的人的体积表示，同时通过运动场，该运动场通过向后的警报将估计的规范表示映射到视频的每个帧。运动场分解成骨骼刚性和非刚性运动，由深网络产生。我们对现有工作显示出显着的性能改进，以及从移动人类的单眼视频的令人尖锐的观点渲染的阐释示例，以挑战不受控制的捕获场景。

神经辐射场（NERF）是一种普遍的视图综合技术，其表示作为连续体积函数的场景，由多层的感知来参数化，其提供每个位置处的体积密度和视图相关的发射辐射。虽然基于NERF的技术在代表精细的几何结构时，具有平稳变化的视图依赖性外观，但它们通常无法精确地捕获和再现光泽表面的外观。我们通过引入Ref-nerf来解决这些限制，该ref-nerf替换了nerf的视图依赖性输出辐射的参数化，使用反射辐射的表示和使用空间不同场景属性的集合来构造该函数的表示。我们展示了与正常载体上的规范器一起，我们的模型显着提高了镜面反射的现实主义和准确性。此外，我们表明我们的模型的外向光线的内部表示是可解释的，可用于场景编辑。

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。

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。

虽然神经辐射场（NERF）已经证明了令人印象深刻的视图合成结果对物体和小型空间区域的结果，但它们在“无界”场景上挣扎，其中相机可以在任何方向上点，并且内容在任何距离处都存在。在此设置中，现有的形式的类似形式模型通常会产生模糊或低分辨率渲染（由于附近和远处物体的不平衡细节和规模），慢慢训练，并且由于任务的固有歧义而可能表现出伪影从一小部分图像重建大场景。我们介绍了MIP-NERF（一个NERF变体，用于解决采样和混叠的NERF变体），其使用非线性场景参数化，在线蒸馏和基于新的失真的常规程序来克服无限性场景所呈现的挑战。我们的模型，我们将“MIP-NERF 360”为瞄准相机围绕一点旋转360度的瞄准场景，与MIP NERF相比将平均平方误差减少54％，并且能够产生逼真的合成视图和用于高度复杂，无限性的现实景区的详细深度图。

我们解决了从由一个未知照明条件照射的物体的多视图图像（及其相机姿势）从多视图图像（和它们的相机姿势）恢复物体的形状和空间变化的空间变化的问题。这使得能够在任意环境照明下呈现对象的新颖视图和对象的材料属性的编辑。我们呼叫神经辐射分解（NERFVERTOR）的方法的关键是蒸馏神经辐射场（NERF）的体积几何形状[MILDENHALL等人。 2020]将物体表示为表面表示，然后在求解空间改变的反射率和环境照明时共同细化几何形状。具体而言，Nerfactor仅使用重新渲染丢失，简单的光滑度Provers以及从真实学中学到的数据驱动的BRDF而无任何监督的表面法线，光可视性，Albedo和双向反射率和双向反射分布函数（BRDF）的3D神经领域-world brdf测量。通过显式建模光可视性，心脏请能够将来自Albedo的阴影分离，并在任意照明条件下合成现实的软或硬阴影。 Nerfactor能够在这场具有挑战性和实际场景的挑战和捕获的捕获设置中恢复令人信服的3D模型进行令人满意的3D模型。定性和定量实验表明，在各种任务中，内容越优于基于经典和基于深度的学习状态。我们的视频，代码和数据可在peoptom.csail.mit.edu/xiuming/projects/nerfactor/上获得。

The rendering procedure used by neural radiance fields (NeRF) samples a scene with a single ray per pixel and may therefore produce renderings that are excessively blurred or aliased when training or testing images observe scene content at different resolutions. The straightforward solution of supersampling by rendering with multiple rays per pixel is impractical for NeRF, because rendering each ray requires querying a multilayer perceptron hundreds of times. Our solution, which we call "mip-NeRF" (à la "mipmap"), extends NeRF to represent the scene at a continuously-valued scale. By efficiently rendering anti-aliased conical frustums instead of rays, mip-NeRF reduces objectionable aliasing artifacts and significantly improves NeRF's ability to represent fine details, while also being 7% faster than NeRF and half the size. Compared to NeRF, mip-NeRF reduces average error rates by 17% on the dataset presented with NeRF and by 60% on a challenging multiscale variant of that dataset that we present. Mip-NeRF is also able to match the accuracy of a brute-force supersampled NeRF on our multiscale dataset while being 22× faster.

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.

We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in lowdimensional problem domains. These results shed light on recent advances in computer vision and graphics that achieve state-of-the-art results by using MLPs to represent complex 3D objects and scenes. Using tools from the neural tangent kernel (NTK) literature, we show that a standard MLP fails to learn high frequencies both in theory and in practice. To overcome this spectral bias, we use a Fourier feature mapping to transform the effective NTK into a stationary kernel with a tunable bandwidth. We suggest an approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities.

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.