《Deep Surface Light Fields》论文调研

0《Deep Surface Light Fields》

摘要：A surface light field represents the radiance of rays originating from any points on the surface in any directions. Traditional approaches require ultra-dense sampling to ensure the rendering quality. In this paper, we present a novel neural network based technique called deep surface light field or DSLF to use only moderate sampling for high fidelity rendering. DSLF automatically fills in the missing data by leveraging different sampling patterns across the vertices and at the same time eliminates redundancies due to the network's prediction capability. For real data, we address the image registration problem as well as conduct texture-aware remeshing for aligning texture edges with vertices to avoid blurring. Comprehensive experiments show that DSLF can further achieve high data compression ratio while facilitating real-time rendering on the GPU. 

翻译：表面光场表示来自表面上任意点、任意方向的光线的辐亮度。传统的方法需要超密集的采样来保证渲染质量。在本文中，我们提出了一种新的基于神经网络的技术，称为深表面光场或DSLF，只使用适度的采样进行高保真渲染。DSLF通过利用跨顶点的不同采样模式自动填充缺失的数据，同时消除了由于网络的预测能力而产生的冗余。对于真实数据，我们解决了图像配准问题，并进行纹理感知重网格，将纹理边缘与顶点对齐以避免模糊。综合实验表明，DSLF在实现GPU实时渲染的同时，还能实现更高的数据压缩比。

1《Multilayer feedforward networks are universal approximators》

摘要：This paper rigorously establishes that standard multilayer feedforward networks with as few as one hidden layer using arbitrary squashing functions are capable of approximating any Borel measurable function from one finite dimensional space to another to any desired degree of accuracy, provided sufficiently many hidden units are available. In this sense, multilayer feedforward networks are a class of universal approximators.

翻译：本文严格地建立了使用任意压缩函数的只有一个隐层的标准多层前馈网络，只要有足够多的隐单元可用，就能够将一个有限维空间中的任意Borel可测函数逼近到另一个有限维空间中的任意精度。从这个意义上说，多层前馈网络是一类通用逼近器。

2《Adam: A Method for Stochastic Optimization》

贡献：This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

翻译：本文介绍了一种基于低阶矩自适应估计的基于梯度的随机目标函数一阶优化算法Adam，并给出了一个收敛速度的遗憾界，其收敛速度可与在线凸优化框架下最著名的结果相媲美。

摘要：We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.

翻译：本文介绍了一种基于低阶矩自适应估计的随机目标函数一阶梯度优化算法Adam。该方法易于实现，计算效率高，内存需求小，对梯度的对角缩放是不变的，非常适合于数据和/或参数方面较大的问题。该方法也适用于非平稳目标和非常嘈杂和/或稀疏梯度的问题。超参数具有直观的解释，通常需要很少的调整。文中还讨论了与亚当启发的相关算法的一些联系。我们还分析了算法的理论收敛性，并给出了一个收敛速度的遗憾界，该收敛速度可与在线凸优化框架下最著名的结果相媲美。实验结果表明，Adam方法在实际应用中效果良好，优于其他随机优化方法。最后，我们讨论了亚当的变体AdaMax，它是基于无穷大范数的。

3《SEEDS: Superpixels Extracted via Energy-Driven Sampling》

贡献：A robust and fast to evaluate energy function is defined, based on enforcing color similarity between the boundaries and the superpixel color histogram, which is able to achieve a performance comparable to the state-of-the-art, but in real-time on a single Intel i7 CPU at 2.8GHz.

翻译：基于边界和超像素颜色直方图之间的颜色相似性，定义了一种鲁棒且快速的能量函数评估方法，能够在2.8GHz的单个Intel i7 CPU上实现与最先进的性能相当的实时性能。

摘要：Superpixel algorithms aim to over-segment the image by grouping pixels that belong to the same object. Many state-of-the-art superpixel algorithms rely on minimizing objective functions to enforce color homogeneity. The optimization is accomplished by sophisticated methods that progressively build the superpixels, typically by adding cuts or growing superpixels. As a result, they are computationally too expensive for real-time applications. We introduce a new approach based on a simple hill-climbing optimization. Starting from an initial superpixel partitioning, it continuously refines the superpixels by modifying the boundaries. We define a robust and fast to evaluate energy function, based on enforcing color similarity between the boundaries and the superpixel color histogram. In a series of experiments, we show that we achieve an excellent compromise between accuracy and efficiency. We are able to achieve a performance comparable to the state-of-the-art, but in real-time on a single Intel i7 CPU at 2.8GHz.

翻译：超像素算法的目标是通过对属于同一目标的像素进行分组来实现图像的过分割。许多最先进的超像素算法依赖于最小化目标函数来实现颜色的同质性。优化是通过复杂的方法逐步构建超像素来完成的，通常是通过添加剪切或增加超像素。因此，对于实时应用程序来说，它们在计算上过于昂贵。我们提出了一种基于简单爬山优化的新方法。该算法从初始超像素划分开始，通过修改边界不断细化超像素。在超像素颜色直方图和边界颜色相似度的基础上，定义了一种鲁棒且快速的能量函数评估方法。在一系列的实验中，我们表明，我们实现了准确性和效率之间的一个很好的折衷。我们能够在2.8GHz的单个Intel i7 CPU上实现与最先进的性能相当的实时性能。

4《Deep Residual Learning for Image Recognition》

贡献：This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

翻译：这项工作提出了一个残差学习框架来简化网络的训练，它比以前使用的那些深度要深得多，并提供了全面的经验证据，表明这些残差网络更容易优化，并且可以从大幅增加的深度中获得精度。

摘要：Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers - 8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

翻译：更深层次的神经网络更难训练。我们提出了一个残差学习框架来简化网络的训练，这些网络比以前使用的网络深度得多。我们明确地将层重新表述为参考层输入学习剩余函数，而不是学习未引用的函数。我们提供了全面的经验证据，表明这些残差网络更容易优化，并且可以在大幅增加深度的情况下获得精度。在ImageNet数据集上，我们评估的残差网深度高达152层——比VGG网[40]深度8倍，但复杂性仍然较低。在ImageNet测试集上，这些残余网络的集合获得了3.57%的误差。该结果在ILSVRC 2015年分类任务中获得第一名。我们还对CIFAR-10进行了100层和1000层的分析。表征的深度对于许多视觉识别任务来说都是至关重要的。仅仅由于我们极深的表示，我们在COCO对象检测数据集上获得了28%的相对改进。深度残差网是我们提交的ILSVRC & COCO 2015竞赛1的基础，在那里我们还获得了ImageNet检测、ImageNet定位、COCO检测和COCO分割任务的第一名。

5《Pixelwise View Selection for Unstructured Multi-View Stereo》

贡献：The core contributions are the joint estimation of depth andnormal information, pixelwise view selection using photometric and geometric priors, and a multi-view geometric consistency term for the simultaneous refinement and image-based depth and normal fusion.

翻译：其核心贡献是深度和正态信息的联合估计，使用光度和几何先验的像素级视图选择，以及用于同时细化和基于图像的深度和正态融合的多视图几何一致性项。

摘要：This work presents a Multi-View Stereo system for robust and efficient dense modeling from unstructured image collections. Our core contributions are the joint estimation of depth and normal information, pixelwise view selection using photometric and geometric priors, and a multi-view geometric consistency term for the simultaneous refinement and image-based depth and normal fusion. Experiments on benchmarks and large-scale Internet photo collections demonstrate state-of-the-art performance in terms of accuracy, completeness, and efficiency.

翻译：本工作提出了一种基于非结构化图像集合的健壮高效密集建模的多视图立体视觉系统。我们的核心贡献包括深度和正态信息的联合估计，使用光度和几何先验的像素级视图选择，以及用于同时细化和基于图像的深度和正态融合的多视图几何一致性项。在基准测试和大规模互联网照片收集上的实验显示了在准确性、完整性和效率方面的最先进的性能。

6《Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks》

贡献：This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.

翻译：本文介绍了一类名为深度卷积生成对抗网络(dcgan)的cnn，它们具有一定的架构约束，并证明了它们是无监督学习的强候选对象。

摘要：In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations.

翻译：近年来，基于卷积网络(cnn)的监督学习在计算机视觉应用中得到了大量应用。相比之下，基于cnn的无监督学习受到的关注较少。在这项工作中，我们希望能够帮助缩小cnn在监督学习和无监督学习方面的成功差距。我们介绍了一类名为深度卷积生成对抗网络(dcgan)的cnn，它们具有一定的架构约束，并证明它们是无监督学习的强候选对象。通过对各种图像数据集的训练，我们展示了令人信服的证据，表明我们的深度卷积对敌对在生成器和鉴别器中学习了从物体部件到场景的层次表示。此外，我们将学习到的特征用于新的任务——证明它们作为一般图像表示的适用性。

7《Image based relighting using neural networks》

贡献：A regression-based method for relighting realworld scenes from a small number of images that approximates matrix segments using neural networks that model light transport as a non-linear function of light source position and pixel coordinates.

翻译：一种基于回归的方法，从少量图像重新照明真实世界场景，使用神经网络近似矩阵段，将光传输建模为光源位置和像素坐标的非线性函数。

摘要：We present a neural network regression method for relighting realworld scenes from a small number of images. The relighting in this work is formulated as the product of the scene's light transport matrix and new lighting vectors, with the light transport matrix reconstructed from the input images. Based on the observation that there should exist non-linear local coherence in the light transport matrix, our method approximates matrix segments using neural networks that model light transport as a non-linear function of light source position and pixel coordinates. Central to this approach is a proposed neural network design which incorporates various elements that facilitate modeling of light transport from a small image set. In contrast to most image based relighting techniques, this regression-based approach allows input images to be captured under arbitrary illumination conditions, including light sources moved freely by hand. We validate our method with light transport data of real scenes containing complex lighting effects, and demonstrate that fewer input images are required in comparison to related techniques.

翻译：我们提出了一种神经网络回归方法来从少量的图像重新照明现实场景。本工作中的重照明是由场景的光传输矩阵和新的光向量的乘积，并由输入图像重建光传输矩阵。基于观察到光传输矩阵中应该存在非线性的局部相干性，我们的方法使用神经网络将光传输建模为光源位置和像素坐标的非线性函数来逼近矩阵段。这种方法的中心是一种被提议的神经网络设计，它包含了各种元素，便于从一个小图像集的光传输建模。与大多数基于图像的重新照明技术相比，这种基于回归的方法允许在任意光照条件下捕捉输入图像，包括用手自由移动的光源。我们用包含复杂灯光效果的真实场景的光传输数据来验证我们的方法，并证明与相关技术相比，需要更少的输入图像。

9《Global illumination with radiance regression functions》

贡献：The approach is to exploit the nonlinear coherence of the indirect illumination data to make the RRF both compact and fast to evaluate, which enables real-time rendering with full global illumination effects, including changing caustics and multiple-bounce high-frequency glossy interreflections.
翻译：该方法利用间接照明数据的非线性相干性，使RRF既紧凑又快速评估，实现实时渲染，具有全全局照明效果，包括变化焦散和多次反射的高频光滑互反射。
摘要：We present radiance regression functions for fast rendering of global illumination in scenes with dynamic local light sources. A radiance regression function (RRF) represents a non-linear mapping from local and contextual attributes of surface points, such as position, viewing direction, and lighting condition, to their indirect illumination values. The RRF is obtained from precomputed shading samples through regression analysis, which determines a function that best fits the shading data. For a given scene, the shading samples are precomputed by an offline renderer. The key idea behind our approach is to exploit the nonlinear coherence of the indirect illumination data to make the RRF both compact and fast to evaluate. We model the RRF as a multilayer acyclic feed-forward neural network, which provides a close functional approximation of the indirect illumination and can be efficiently evaluated at run time. To effectively model scenes with spatially variant material properties, we utilize an augmented set of attributes as input to the neural network RRF to reduce the amount of inference that the network needs to perform. To handle scenes with greater geometric complexity, we partition the input space of the RRF model and represent the subspaces with separate, smaller RRFs that can be evaluated more rapidly. As a result, the RRF model scales well to increasingly complex scene geometry and material variation. Because of its compactness and ease of evaluation, the RRF model enables real-time rendering with full global illumination effects, including changing caustics and multiple-bounce high-frequency glossy interreflections.

翻译：针对具有动态局部光源的场景，提出了亮度回归函数来实现全局光照的快速渲染。亮度回归函数(RRF)表示表面点的局部和上下文属性的非线性映射，例如位置、观察方向和照明条件，到它们的间接照明值。RRF是通过回归分析从预先计算的阴影样本中获得的，它确定了一个最适合阴影数据的函数。对于给定的场景，阴影样本是由离线渲染器预先计算的。我们的方法背后的关键思想是利用间接照明数据的非线性相干性，使RRF既紧凑又快速评估。我们将RRF建模为一个多层无环前馈神经网络，它提供了间接照明的一个接近的函数近似，并可以在运行时有效地评估。为了有效地模拟具有空间不同材料属性的场景，我们利用一个扩充的属性集作为神经网络RRF的输入，以减少网络需要执行的推理量。为了处理具有较大几何复杂性的场景，我们对RRF模型的输入空间进行划分，并使用独立的、更小的RRF来表示子空间，这样可以更快地进行评估。因此，RRF模型可以很好地扩展到日益复杂的场景几何和材料变化。由于其紧凑和易于评估，RRF模型可以实现实时渲染，具有全全局照明效果，包括变化焦散和多次反射的高频光滑互反射。

10《Learning based compression of surface light fields for real-time rendering of global illumination scenes》

贡献：An algorithm for compression and real-time rendering of surface light fields (SLF) encoding the visual appearance of objects in static scenes with high frequency variations and introduces a learning based approach, Clustered Exemplar Orthogonal Bases (CEOB), which trains a compact dictionary of orthogonal basis pairs, enabling efficient sparse projection of the SLF data.
翻译：一种表面光场(SLF)的压缩和实时渲染算法，编码静态场景中具有高频变化的物体的视觉外观，并引入了一种基于学习的方法，即聚类范例正交基对(CEOB)，它训练一个紧凑的正交基对字典，实现SLF数据的高效稀疏投影。
摘要：We present an algorithm for compression and real-time rendering of surface light fields (SLF) encoding the visual appearance of objects in static scenes with high frequency variations. We apply a non-local clustering in order to exploit spatial coherence in the SLF data. To efficiently encode the data in each cluster, we introduce a learning based approach, Clustered Exemplar Orthogonal Bases (CEOB), which trains a compact dictionary of orthogonal basis pairs, enabling efficient sparse projection of the SLF data. In addition, we discuss the application of the traditional Clustered Principal Component Analysis (CPCA) on SLF data, and show that in most cases, CEOB outperforms CPCA, K-SVD and spherical harmonics in terms of memory footprint, rendering performance and reconstruction quality. Our method enables efficient reconstruction and real-time rendering of scenes with complex materials and light sources, not possible to render in real-time using previous methods.

翻译：我们提出了一种表面光场(SLF)的压缩和实时渲染算法，编码了静态场景中物体的高频变化的视觉外观。我们应用非局部聚类来利用SLF数据中的空间一致性。为了在每个聚类中有效地编码数据，我们引入了一种基于学习的方法，即聚类范例正交基对(CEOB)，它训练了一个紧凑的正交基对字典，实现了SLF数据的高效稀疏投影。此外，我们讨论了传统的聚类主成分分析(CPCA)在SLF数据上的应用，并表明在大多数情况下，CEOB在内存占用、渲染性能和重构质量方面都优于CPCA、K-SVD和球形谐波。我们的方法能够高效地重建和实时渲染具有复杂材质和光源的场景，这是以前的方法无法实时渲染的。

11《Parallel View-Dependent Level-of-Detail Control》

贡献：This work selectively refines and coarsens an arbitrary triangle mesh at the granularity of individual vertices to create meshes that are highly adapted to dynamic view parameters and shows that by introducing new data structures and dependency rules, one can realize fine-grain progressive mesh updates as a sequence of parallel streaming passes over the mesh elements.
翻译：这项工作有选择地在单个顶点的粒度上细化和粗化任意三角形网格，以创建高度适应动态视图参数的网格，并表明通过引入新的数据结构和依赖规则，可以通过一系列并行流通过网格元素来实现细粒度的渐进式网格更新。
摘要：We present a scheme for view-dependent level-of-detail control that is implemented entirely on programmable graphics hardware. Our scheme selectively refines and coarsens an arbitrary triangle mesh at the granularity of individual vertices to create meshes that are highly adapted to dynamic view parameters. Such fine-grain control has previously been demonstrated using sequential CPU algorithms. However, these algorithms involve pointer-based structures with intricate dependencies that cannot be handled efficiently within the restricted framework of GPU parallelism. We show that by introducing new data structures and dependency rules, one can realize fine-grain progressive mesh updates as a sequence of parallel streaming passes over the mesh elements. A major design challenge is that the GPU processes stream elements in isolation. The mesh update algorithm has time complexity proportional to the selectively refined mesh, and moreover, can be amortized across several frames. The result is a single standard index buffer that can be used directly for rendering. The static data structure is remarkably compact, requiring only 57 percent more memory than an indexed triangle list. We demonstrate real-time exploration of complex models with normals and textures, as well as shadowing and semitransparent surface rendering applications that make direct use of the resulting dynamic index buffer.

翻译：我们提出了一个完全在可编程图形硬件上实现的视图依赖的详细级别控制方案。我们的方案有选择地在单个顶点的粒度上对任意三角形网格进行细化和粗化，以创建高度适应动态视图参数的网格。这种细粒度控制以前已经使用顺序CPU算法演示过。然而，这些算法涉及到基于指针的结构，具有复杂的依赖关系，不能在GPU并行性的限制框架内有效地处理。我们证明，通过引入新的数据结构和依赖规则，可以实现细粒度的渐进网格更新，因为并行流序列通过网格元素。一个主要的设计挑战是GPU独立处理流元素。网格更新算法的时间复杂度与有选择性的细化网格成正比，并且可以在多个帧之间平摊。结果是一个单一的标准索引缓冲区，可以直接用于呈现。静态数据结构非常紧凑，只需要比索引三角形列表多57%的内存。我们演示了使用法线和纹理的复杂模型的实时探索，以及直接使用产生的动态索引缓冲区的阴影和半透明表面渲染应用程序。

12《Rectified Linear Units Improve Restricted Boltzmann Machines》

贡献：Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
翻译：受限玻尔兹曼机是使用二进制随机隐藏单元开发的，它学习的特征对NORB数据集上的对象识别和野生数据集上的Labeled Faces的人脸验证更有帮助。
摘要：Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all have the same weights but have progressively more negative biases. The learning and inference rules for these "Stepped Sigmoid Units" are unchanged. They can be approximated efficiently by noisy, rectified linear units. Compared with binary units, these units learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset. Unlike binary units, rectified linear units preserve information about relative intensities as information travels through multiple layers of feature detectors.

翻译：利用二元随机隐单元开发了受限玻尔兹曼机。通过将每个二进制单元替换为无限数量的副本，这些副本具有相同的权重，但具有越来越多的负面偏见，可以推广这些方法。这些“阶梯形Sigmoid单元”的学习和推理规则没有改变。它们可以用有噪声的整流线性单元有效地逼近。与二进制单元相比，这些单元学习的特征更适合在NORB数据集上进行对象识别，在Wild数据集上进行Labeled Faces的人脸验证。与二进制单元不同，当信息通过多层特征检测器时，纠偏线性单元保留了有关相对强度的信息。

13《EPnP: An Accurate O(n) Solution to the PnP Problem》

贡献：A non-iterative solution to the PnP problem—the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences—whose computational complexity grows linearly with n, which can be done in O(n) time by expressing these coordinates as weighted sum of the eigenvectors of a 12×12 matrix.
翻译：PnP问题的非迭代解——标定相机的位姿从n个3d到2d点对应关系的估计——其计算复杂度随n线性增长，通过将这些坐标表示为12×12矩阵的特征向量的加权和，可以在O(n)时间内完成。
摘要：We propose a non-iterative solution to the PnP problem—the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences—whose computational complexity grows linearly with n. This is in contrast to state-of-the-art methods that are O(n5) or even O(n8), without being more accurate. Our method is applicable for all n≥4 and handles properly both planar and non-planar configurations. Our central idea is to express the n 3D points as a weighted sum of four virtual control points. The problem then reduces to estimating the coordinates of these control points in the camera referential, which can be done in O(n) time by expressing these coordinates as weighted sum of the eigenvectors of a 12×12 matrix and solving a small constant number of quadratic equations to pick the right weights. Furthermore, if maximal precision is required, the output of the closed-form solution can be used to initialize a Gauss-Newton scheme, which improves accuracy with negligible amount of additional time. The advantages of our method are demonstrated by thorough testing on both synthetic and real-data. 

翻译：PnP型问题我们建议非迭代解估计校准相机的姿势从n 3 d-to-2d点correspondences-whose计算复杂度增长线性与n。这与最先进的方法,(它们)甚至O (n8),而不会被更准确。我们的方法适用于所有n≥4的构型，并能正确处理平面和非平面构型。我们的中心思想是将n个三维点表示为四个虚拟控制点的加权和。问题然后减少估计这些控制点的坐标相机引用,这可以通过O (n)时间表达这些坐标的加权和12×12矩阵的特征向量和解决小二次方程的常数选择正确的重量。此外，如果需要最大的精度，封闭形式的解的输出可以用来初始化一个高斯-牛顿方案，这可以提高精度与微不足道的额外时间。通过对合成数据和实际数据的测试，验证了该方法的优越性。

14《Real-time high-quality View-Dependent Texture Mapping using per-pixel visibility》

贡献：This work combines a hybrid geometric and image-based representation of a given 3D object to speed-up rendering at the cost of a little loss of visual accuracy, allowing rendering of complex geometric meshes at high frame rates without usual blurring or skinning artifacts.
翻译：这项工作结合了一个给定的3D对象的几何和基于图像的混合表示，以牺牲一点视觉精度为代价来加速渲染，允许在高帧率下渲染复杂的几何网格，而不需要通常的模糊或皮肤工件。
摘要：We present an extension of View-Dependent Texture Mapping (VDTM) allowing rendering of complex geometric meshes at high frame rates without usual blurring or skinning artifacts. We combine a hybrid geometric and image-based representation of a given 3D object to speed-up rendering at the cost of a little loss of visual accuracy.During a precomputation step, we store an image-based version of the original mesh by simply and quickly computing textures from viewpoints positionned around it by the user. During the rendering step, we use these textures in order to map on the fly colors and geometric details onto the surface of a low-polygon-count version of the mesh.Real-time rendering is achieved while combining up to three viewpoints at a time, using pixel shaders. No parameterization of the mesh is needed and occlusion effects are taken into account while computing on the fly the best viewpoints for a given pixel. Moreover, the integration of this method in common real-time rendering systems is straightforward and allows applying self-shadowing as well as other z-buffer effects.

翻译：我们提出了一种基于视图的纹理映射(VDTM)的扩展，允许在高帧率下渲染复杂的几何网格，而不会出现通常的模糊或皮肤工件。我们将给定的3D对象的几何和基于图像的混合表示结合起来，以加快渲染速度，但代价是视觉精度有所下降。在预计算步骤中，我们通过简单快速地计算用户在原始网格周围的视点的纹理来存储基于图像的版本。在渲染步骤中，我们使用这些纹理，以便将苍蝇的颜色和几何细节映射到一个低多边形数版本的网格的表面。实时渲染是通过使用像素着色器在一次结合三个视点来实现的。网格不需要参数化，在计算给定像素的最佳视点时，将遮挡效果考虑进去。此外，这种方法集成在常见的实时渲染系统中是直接的，并允许应用自阴影和其他z缓冲效果。

15《Complete Solution Classification for the Perspective-Three-Point Problem》

贡献：This work uses Wu-Ritt's zero decomposition algorithm to give a complete triangular decomposition for the P3P equation system, and gives some pure geometric criteria for the number of real physical solutions.
翻译：本文利用Wu-Ritt的零分解算法对P3P方程系统进行了完全三角分解，并给出了实际物理解个数的一些纯几何准则。
摘要：We use two approaches to solve the perspective-three-point (P3P) problem: the algebraic approach and the geometric approach. In the algebraic approach, we use Wu-Ritt's zero decomposition algorithm to give a complete triangular decomposition for the P3P equation system. This decomposition provides the first complete analytical solution to the P3P problem. We also give a complete solution classification for the P3P equation system, i.e., we give explicit criteria for the P3P problem to have one, two, three, and four solutions. Combining the analytical solutions with the criteria, we provide an algorithm, CASSC, which may be used to find complete and robust numerical solutions to the P3P problem. In the geometric approach, we give some pure geometric criteria for the number of real physical solutions. 

翻译：我们使用两种方法来解决透视三点(P3P)问题:代数方法和几何方法。在代数方法中，我们使用Wu-Ritt的零分解算法对P3P方程系统进行完整的三角分解。这种分解为P3P问题提供了第一个完整的解析解。我们也为P3P方程系统给出了一个完整的解分类，即，我们给出了P3P问题有一个、两个、三个和四个解的明确标准。将解析解与准则相结合，我们提出了一种求解P3P问题的完整稳健数值解的CASSC算法。在几何方法中，我们给出了真实物理解数目的一些纯几何准则。

17《Light field mapping: efficient representation and hardware rendering of surface light fields》

贡献：A compact representation suitable for an accelerated graphics pipeline to enable the use of surface light fields in real-time rendering is developed and a new method of approximating the light field data is implemented that produces positive only factors allowing for faster rendering using simpler graphics hardware than earlier methods.
翻译：紧凑表示适合加速图形管道,使表面光场实时渲染的使用是发达国家和一种新的近似方法实现光场数据只产生积极因素允许更快的渲染比早些时候方法使用简单的图形硬件。

摘要：A light field parameterized on the surface offers a natural and intuitive description of the view-dependent appearance of scenes with complex reflectance properties. To enable the use of surface light fields in real-time rendering we develop a compact representation suitable for an accelerated graphics pipeline. We propose to approximate the light field data by partitioning it over elementary surface primitives and factorizing each part into a small set of lower-dimensional functions. We show that our representation can be further compressed using standard image compression techniques leading to extremely compact data sets that are up to four orders of magnitude smaller than the input data. Finally, we develop an image-based rendering method, light field mapping, that can visualize surface light fields directly from this compact representation at interactive frame rates on a personal computer. We also implement a new method of approximating the light field data that produces positive only factors allowing for faster rendering using simpler graphics hardware than earlier methods. We demonstrate the results for a variety of non-trivial synthetic scenes and physical objects scanned through 3D photography. 
翻译：一个参数化的光场在表面上提供了一个自然和直观的描述，视视依赖场景的外观具有复杂的反射特性。为了在实时渲染中使用表面光场，我们开发了一种适用于加速图形管道的紧凑表示。我们建议通过将光场数据划分为基本表面基元，并将每个部分分解为一个小的低维函数集来近似光场数据。我们表明，我们的表示可以使用标准的图像压缩技术进一步压缩，从而得到比输入数据小四个数量级的极其紧凑的数据集。最后，我们开发了一种基于图像的渲染方法，光场映射，可以直接从这种紧凑的表示在个人计算机上以交互帧率显示表面光场。我们还实现了一种新的近似光场数据的方法，这种方法产生的只有正因子，允许使用更简单的图形硬件比以前的方法更快的渲染。我们演示了通过3D摄影扫描的各种非平凡的合成场景和物理对象的结果。

18《Unstructured lumigraph rendering》

摘要：We describe an image based rendering approach that generalizes many current image based rendering algorithms, including light field rendering and view-dependent texture mapping. In particular, it allows for lumigraph-style rendering from a set of input cameras in arbitrary configurations (i.e., not restricted to a plane or to any specific manifold). In the case of regular and planar input camera positions, our algorithm reduces to a typical lumigraph approach. When presented with fewer cameras and good approximate geometry, our algorithm behaves like view-dependent texture mapping. The algorithm achieves this flexibility because it is designed to meet a set of specific goals that we describe. We demonstrate this flexibility with a variety of examples.
翻译：我们描述了一种基于图像的渲染方法，该方法概括了当前基于图像的渲染算法，包括光场渲染和视图相关的纹理映射。特别是，它允许从一组输入相机以任意配置(即，不局限于一个平面或任何特定的流形)进行lumigraphstyle渲染。在常规和平面输入相机位置的情况下，我们的算法简化为一个典型的lumigraph方法。当呈现较少的相机和良好的近似几何时，我们的算法表现得像视图相关的纹理映射。该算法之所以具有这种灵活性，是因为它的设计是为了满足我们所描述的一组特定目标。我们通过各种示例来演示这种灵活性。

19《Surface light fields for 3D photography》

贡献：This paper presents a framework for construction, compression, interactive rendering, and rudimentary editing of surface light fields of real objects, incorporating view-dependent geometric level-of-detail control.
翻译：本文提出了一个框架，用于构造、压缩、交互渲染和基本编辑真实物体的表面光场，并结合了视相关的几何细节水平控制。
摘要：A surface light field is a function that assigns a color to each ray originating on a surface. Surface light fields are well suited to constructing virtual images of shiny objects under complex lighting conditions. This paper presents a framework for construction, compression, interactive rendering, and rudimentary editing of surface light fields of real objects. Generalization of vector quantization and principal component analysis are used to construct a compressed representation of an object's surface light field from photographs and range scans. A new rendering algorithm achieves interactive rendering of images from the compressed representation, incorporating view-dependent geometric level-of-detail control. The surface light field representation can also be directly edited to yield plausible surface light fields for small changes in surface geometry and reflectance properties. 

翻译：表面光场是一个函数，它为表面上发出的每一束光线赋予一种颜色。表面光场非常适合于构造复杂光照条件下闪亮物体的虚拟图像。本文提出了一个用于构造、压缩、交互渲染和基本编辑真实物体表面光场的框架。利用矢量量化和主成分分析的泛化方法，从照片和距离扫描中构造物体表面光场的压缩表示。一种新的渲染算法实现了图像的交互式渲染，结合了视相关的几何细节水平控制。表面光场表示也可以直接编辑，以产生表面几何形状和反射特性的微小变化的似是而非的表面光场。

20《Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences》

摘要：Artificial neural networks are appearing as useful alternatives to traditional statistical modelling techniques in many scientific disciplines. This paper presents a general introduction and discussion of recent applications of the multilayer perceptron, one type of artificial neural network, in the atmospheric sciences.
翻译：人工神经网络正在许多科学学科中作为传统统计建模技术的有用替代品出现。本文对多层感知器(一种人工神经网络)在大气科学中的最新应用作了概述和讨论。

21《Lazy Decompression of Surface Light Fields for Precomputed Global Illumination》

贡献：A lazy decompression scheme is presented which allows for high-quality compression by making use of block-coding techniques and takes advantage of spatial coherence within the light field to aid compression.
翻译：提出了一种延迟解压缩方案，该方案利用分组编码技术和光场内的空间一致性来辅助压缩，从而实现高质量的压缩。
摘要：This paper describes a series of algorithms that allow the unconstrained walkthrough of static scenes shaded with the results of precomputed global illumination. The global illumination includes specular as well as diffuse terms, and intermediate results are cached as surface light fields. The compression of such light fields is examined, and a lazy decompression scheme is presented which allows for high-quality compression by making use of block-coding techniques. This scheme takes advantage of spatial coherence within the light field to aid compression, and also makes use of temporal coherence to accelerate decompression. Finally the techniques are extended to a certain type of dynamic scene. 

翻译：本文描述了一系列的算法，允许使用预先计算的全局光照结果对静态场景进行无约束的遍历。全局照明包括镜面照明和漫反射照明，中间结果缓存为表面光场。研究了这种光场的压缩，并提出了一种延迟解压缩方案，该方案通过使用块编码技术允许高质量的压缩。该方案利用光场内的空间相干性来辅助压缩，同时利用时间相干性来加速压缩。最后将该技术推广到某一类动态场景中。

23《Light field rendering》

贡献：This paper describes a sampled representation for light fields that allows for both efficient creation and display of inward and outward looking views, and describes a compression system that is able to compress the light fields generated by more than a factor of 100:1 with very little loss of fidelity.
翻译：本文描述了光场的采样表示,允许有效的创建和显示的出入口视图,并描述了一个压缩系统,能够产生的光场压缩一个多因素的100:1很少忠诚的损失。

摘要：A number of techniques have been proposed for flying through scenes by redisplaying previously rendered or digitized views. Techniques have also been proposed for interpolating between views by warping input images, using depth information or correspondences between multiple images. In this paper, we describe a simple and robust method for generating new views from arbitrary camera positions without depth information or feature matching, simply by combining and resampling the available images. The key to this technique lies in interpreting the input images as 2D slices of a 4D function the light field. This function completely characterizes the flow of light through unobstructed space in a static scene with fixed illumination. We describe a sampled representation for light fields that allows for both efficient creation and display of inward and outward looking views. We hav e created light fields from large arrays of both rendered and digitized images. The latter are acquired using a video camera mounted on a computer-controlled gantry. Once a light field has been created, new views may be constructed in real time by extracting slices in appropriate directions. Since the success of the method depends on having a high sample rate, we describe a compression system that is able to compress the light fields we have generated by more than a factor of 100:1 with very little loss of fidelity. We also address the issues of antialiasing during creation, and resampling during slice extraction. CR Categories: I.3.2 [Computer Graphics]: Picture/Image Generation — Digitizing and scanning, Viewing algorithms; I.4.2 [Computer Graphics]: Compression — Approximate methods Additional keywords: image-based rendering, light field, holographic stereogram, vector quantization, epipolar analysis

翻译：通过重新显示以前渲染过的或数字化的视图，已经提出了许多技术来在场景中飞行。也有人提出通过扭曲输入图像、利用深度信息或多幅图像之间的对应来在视图之间进行插值的技术。在本文中，我们描述了一种简单而稳健的方法，可以在没有深度信息或特征匹配的情况下，从任意相机位置生成新的视图，只需简单地组合和重采样可用的图像。该技术的关键在于将输入图像解释为光场的4D函数的2D切片。这个功能完全体现了光在固定照明的静态场景中通过无遮挡空间的流动。我们描述了一个光场的采样表示，它允许有效地创建和显示内向和外向的视图。我们已经从大量的渲染和数字化图像中创建了光场。。后者是通过安装在计算机控制的机架上的摄像机获得的。一旦创建了一个光场，就可以通过在适当的方向提取切片来实时构建新的视图。由于该方法的成功依赖于高采样率，我们描述了一个压缩系统，该系统能够将我们产生的光场压缩超过100:1倍，保真度损失很小。我们还解决了创建过程中的抗锯齿问题，以及切片提取过程中的重采样问题。CR类别:I.3.2[计算机图形学]:图像/图像生成-数字化和扫描、查看算法;附加关键词:基于图像的渲染，光场，全息立体图，矢量量化，外极分析。

24《Plenoptic modeling: an image-based rendering system》

贡献：An image-based rendering system based on sampling, reconstructing, and resampling the plenoptic function is presented and a novel visible surface algorithm and a geometric invariant for cylindrical projections that is equivalent to the epipolar constraint defined for planar projections are introduced.
翻译：提出了一种基于全光函数采样、重构和重采样的图像绘制系统，并介绍了一种新的可见面算法和一种等价于平面投影的外极约束的柱面投影几何不变量。
摘要：Image-based rendering is a powerful new approach for generating real-time photorealistic computer graphics. It can provide convincing animations without an explicit geometric representation. We use the “plenoptic function” of Adelson and Bergen to provide a concise problem statement for image-based rendering paradigms, such as morphing and view interpolation. The plenoptic function is a parameterized function for describing everything that is visible from a given point in space. We present an image-based rendering system based on sampling, reconstructing, and resampling the plenoptic function. In addition, we introduce a novel visible surface algorithm and a geometric invariant for cylindrical projections that is equivalent to the epipolar constraint defined for planar projections.

翻译：基于图像的绘制是一种强大的生成实时真实感计算机图形的新方法。它可以提供令人信服的动画，而无需明确的几何表示。我们使用Adelson和Bergen的“全光函数”为基于图像的渲染范例(如变形和视图插值)提供了一个简明的问题陈述。全光学函数是一个参数化的函数，用于描述从空间中给定点可见的一切。提出了一种基于全光函数采样、重构和重采样的图像绘制系统。此外，我们引入了一种新的可见曲面算法和一个柱面投影的几何不变量，该不变量等价于平面投影的外极约束。
 

25《Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography》

贡献：New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
翻译：新的结果是在获得一个解决方案所需的最小地标数上推导出来的，并提出了计算这些最小地标解的算法，以封闭的形式，这为一个自动系统提供了基础，该系统可以解决困难观测下的位置确定问题。
摘要：A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing

翻译：提出了一种新的模型拟合方法——随机样本共识(RANSAC)。RANSAC能够解释/平滑包含大量粗误差的数据，因此非常适合于基于易出错特征检测器提供的数据进行解释的自动图像分析应用。本文主要描述了RANSAC在位置确定问题(LDP)中的应用:给定一幅描述一组已知位置的地标的图像，确定该图像所从的空间点。为了响应RANSAC的要求，我们在获得解所需的最小地标数的基础上推导出新的结果，并给出了以封闭形式计算这些最小地标解的算法。这些结果为开发一个能够解决难查看LDP的自动化系统提供了依据。

28《On Information and Sufficiency》

摘要：Project Euclid - mathematics and statistics online

翻译：欧几里得计画-在线数学与统计