Existing methods for the 4D reconstruction of general, non-rigidly deforming objects focus on novel-view synthesis and neglect correspondences. However, time consistency enables advanced downstream tasks like 3D editing, motion analysis, or virtual-asset creation. We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner. Our dynamic-NeRF method takes multi-view RGB videos and background images from static cameras with known camera parameters as input. It then reconstructs the deformations of an estimated canonical model of the geometry and appearance in an online fashion. Since this canonical model is time-invariant, we obtain correspondences even for long-term, long-range motions. We employ neural scene representations to parametrize the components of our method. Like prior dynamic-NeRF methods, we use a backwards deformation model. We find nontrivial adaptations of this model necessary to handle larger motions: We decompose the deformations into a strongly regularized coarse component and a weakly regularized fine component, where the coarse component also extends the deformation field into the space surrounding the object, which enables tracking over time. We show experimentally that, unlike prior work that only handles small motion, our method enables the reconstruction of studio-scale motions.

The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. Both problems are highly challenging, because hair has complex geometry and appearance and exhibits challenging motion. In this paper, we present a two-stage approach that models hair independently of the head to address these challenges in a data-driven manner. The first stage, state compression, learns a low-dimensional latent space of 3D hair states including motion and appearance via a novel autoencoder-as-a-tracker strategy. To better disentangle the hair and head in appearance learning, we employ multi-view hair segmentation masks in combination with a differentiable volumetric renderer. The second stage optimizes a novel hair dynamics model that performs temporal hair transfer based on the discovered latent codes. To enforce higher stability while driving our dynamics model, we employ the 3D point-cloud autoencoder from the compression stage for denoising of the hair state. Our model outperforms the state of the art in novel view synthesis and is capable of creating novel hair animations without relying on hair observations as a driving signal.††Project page at https://ziyanwl.github.io/neuwigs/.

Recent methods for 3D reconstruction and rendering increasingly benefit from end-to-end optimization of the entire image formation process. However, this approach is currently limited: effects of the optical hardware stack and in particular lenses are hard to model in a unified way. This limits the quality that can be achieved for camera calibration and the fidelity of the results of 3D reconstruction. In this paper, we propose NeuroLens, a neural lens model for distortion and vignetting that can be used for point projection and ray casting and can be optimized through both operations. This means that it can (optionally) be used to perform pre-capture calibration using classical calibration targets, and can later be used to perform calibration or refinement during 3D reconstruction, e.g., while optimizing a radiance field. To evaluate the performance of our proposed model, we create a comprehensive dataset assembled from the Lensfun database with a multitude of lenses. Using this and other real-world datasets, we show that the quality of our proposed lens model outperforms standard packages as well as recent approaches while being much easier to use and extend. The model generalizes across many lens types and is trivial to integrate into existing 3D reconstruction and rendering systems. Visit our project website at: https://neural-lens.github.io.

We present Virtual Elastic Objects (VEOs): virtual objects that not only look like their real-world counterparts but also behave like them, even when subject to novel interactions. Achieving this presents multiple challenges: not only do objects have to be captured including the physical forces acting on them, then faithfully reconstructed and rendered, but also plausible material parameters found and simulated. To create VEOs, we built a multi-view capture system that captures objects under the influence of a compressed air stream. Building on recent advances in model-free, dynamic Neural Radiance Fields, we reconstruct the objects and corresponding deformation fields. We propose to use a differentiable, particle-based simulator to use these deformation fields to find representative material parameters, which enable us to run new simulations. To render simulated objects, we devise a method for integrating the simulation results with Neural Radiance Fields. The resulting method is applicable to a wide range of scenarios: it can handle objects composed of inhomogeneous material, with very different shapes, and it can simulate interactions with other virtual objects. We present our results using a newly collected dataset of 12 objects under a variety of force fields, which will be made available upon publication.

We propose a novel approach for 3D video synthesis that is able to represent multi-view video recordings of a dynamic real-world scene in a compact, yet expressive representation that enables high-quality view synthesis and motion interpolation. Our approach takes the high quality and compactness of static neural radiance fields in a new direction: to a model-free, dynamic setting. At the core of our approach is a novel time-conditioned neural radiance field that represents scene dynamics using a set of compact latent codes. We are able to significantly boost the training speed and perceptual quality of the generated imagery by a novel hierarchical training scheme in combination with ray importance sampling. Our learned representation is highly compact and able to represent a 10 second 30 FPS multi-view video recording by 18 cameras with a model size of only 28MB. We demonstrate that our method can render high-fidelity wide-angle novel views at over 1K resolution, even for complex and dynamic scenes. We perform an extensive qualitative and quantitative evaluation that shows that our approach outperforms the state of the art. Project website: https://neural-3d-video.github.io/.

Capturing and rendering life-like hair is particularly challenging due to its fine geometric structure, the complex physical interaction and its non-trivial visual appearance. Yet, hair is a critical component for believable avatars. In this paper, we address the aforementioned problems: 1) we use a novel, volumetric hair representation that is composed of thousands of primitives. Each primitive can be rendered efficiently, yet realistically, by building on the latest advances in neural rendering. 2) To have a reliable control signal, we present a novel way of tracking hair on the strand level. To keep the computational effort manageable, we use guide hairs and classic techniques to expand those into a dense hood of hair. 3) To better enforce temporal consistency and generalization ability of our model, we further optimize the 3D scene flow of our representation with multiview optical flow, using volumetric raymarching. Our method can not only create realistic renders of recorded multi-view sequences, but also create renderings for new hair configurations by providing new control signals. We compare our method with existing work on viewpoint synthesis and drivable animation and achieve state-of-the-art results. https://ziyanw1.github.io/hvh.

Learning geometry, motion, and appearance priors of object classes is important for the solution of a large variety of computer vision problems. While the majority of approaches has focused on static objects, dynamic objects, especially with controllable articulation, are less explored. We propose a novel approach for learning a representation of the geometry, appearance, and motion of a class of articulated objects given only a set of color images as input. In a self-supervised manner, our novel representation learns shape, appearance, and articulation codes that enable independent control of these semantic dimensions. Our model is trained end-to-end without requiring any articulation annotations. Experiments show that our approach performs well for different joint types, such as revolute and prismatic joints, as well as different combinations of these joints. Compared to state of the art that uses direct 3D supervision and does not output appearance, we recover more faithful geometry and appearance from 2D observations only. In addition, our representation enables a large variety of applications, such as few-shot reconstruction, the generation of novel articulations, and novel view-synthesis. Project page: https://weify627.github.io/nasam/.

Abstract Synthesizing photo‐realistic images and videos is at the heart of computer graphics and has been the focus of decades of research. Traditionally, synthetic images of a scene are generated using rendering algorithms such as rasterization or ray tracing, which take specifically defined representations of geometry and material properties as input. Collectively, these inputs define the actual scene and what is rendered, and are referred to as the scene representation (where a scene consists of one or more objects). Example scene representations are triangle meshes with accompanied textures (e.g., created by an artist), point clouds (e.g., from a depth sensor), volumetric grids (e.g., from a CT scan), or implicit surface functions (e.g., truncated signed distance fields). The reconstruction of such a scene representation from observations using differentiable rendering losses is known as inverse graphics or inverse rendering. Neural rendering is closely related, and combines ideas from classical computer graphics and machine learning to create algorithms for synthesizing images from real‐world observations. Neural rendering is a leap forward towards the goal of synthesizing photo‐realistic image and video content. In recent years, we have seen immense progress in this field through hundreds of publications that show different ways to inject learnable components into the rendering pipeline. This state‐of‐the‐art report on advances in neural rendering focuses on methods that combine classical rendering principles with learned 3D scene representations, often now referred to as neural scene representations. A key advantage of these methods is that they are 3D‐consistent by design, enabling applications such as novel viewpoint synthesis of a captured scene. In addition to methods that handle static scenes, we cover neural scene representations for modeling non‐rigidly deforming objects and scene editing and composition. While most of these approaches are scene‐specific, we also discuss techniques that generalize across object classes and can be used for generative tasks. In addition to reviewing these state‐of‐the‐art methods, we provide an overview of fundamental concepts and definitions used in the current literature. We conclude with a discussion on open challenges and social implications.

Boundary integrals are unique to physics-based differentiable rendering and crucial for differentiating with respect to object geometry. Under the differential path integral framework---which has enabled the development of sophisticated differentiable rendering algorithms---the boundary components are themselves path integrals. Previously, although the mathematical formulation of boundary path integrals have been established, efficient estimation of these integrals remains challenging. In this paper, we introduce a new technique to efficiently estimate boundary path integrals. A key component of our technique is a primary-sample-space guiding step for importance sampling of boundary segments. Additionally, we show multiple importance sampling can be used to combine multiple guided samplings. Lastly, we introduce an optional edge sorting step to further improve the runtime performance. We evaluate the effectiveness of our method using several differentiable-rendering and inverse-rendering examples and provide comparisons with existing methods for reconstruction as well as gradient quality.

We propose Pulsar, an efficient sphere-based differentiable rendering module that is orders of magnitude faster than competing techniques, modular, and easy-to-use due to its tight integration with PyTorch. Differentiable rendering is the foundation for modern neural rendering approaches, since it enables end-to-end training of 3D scene representations from image observations. However, gradient-based optimization of neural mesh, voxel, or function representations suffers from multiple challenges, i.e., topological in-consistencies, high memory footprints, or slow rendering speeds. To alleviate these problems, Pulsar employs: 1) a sphere-based scene representation, 2) a modular, efficient differentiable projection operation, and 3) (optional) neural shading. Pulsar executes orders of magnitude faster than existing techniques and allows real-time rendering and optimization of representations with millions of spheres. Using spheres for the scene representation, unprecedented speed is obtained while avoiding topology problems. Pulsar is fully differentiable and thus enables a plethora of applications, ranging from 3D reconstruction to neural rendering.

The combination of traditional rendering with neural networks in Deferred Neural Rendering (DNR) [38] provides a compelling balance between computational complexity and realism of the resulting images. Using skinned meshes for rendering articulating objects is a natural extension for the DNR framework and would open it up to a plethora of applications. However, in this case the neural shading step must account for deformations that are possibly not captured in the mesh, as well as alignment in-accuracies and dynamics—which can confound the DNR pipeline. We present Articulated Neural Rendering (ANR), a novel framework based on DNR which explicitly addresses its limitations for virtual human avatars. We show the superiority of ANR not only with respect to DNR but also with methods specialized for avatar creation and animation. In two user studies, we observe a clear preference for our avatar model and we demonstrate state-of-the-art performance on quantitative evaluation metrics. Perceptually, we observe better temporal stability, level of detail and plausibility. More results are available at our project page: https://anr-avatars.github.io.

We present Non-Rigid Neural Radiance Fields (NR-NeRF), a reconstruction and novel view synthesis approach for general non-rigid dynamic scenes. Our approach takes RGB images of a dynamic scene as input (e.g., from a monocular video recording), and creates a high-quality space-time geometry and appearance representation. We show that a single handheld consumer-grade camera is sufficient to synthesize sophisticated renderings of a dynamic scene from novel virtual camera views, e.g. a ‘bullet-time’ video effect. NR-NeRF disentangles the dynamic scene into a canonical volume and its deformation. Scene deformation is implemented as ray bending, where straight rays are deformed non-rigidly. We also propose a novel rigidity network to better constrain rigid regions of the scene, leading to more stable results. The ray bending and rigidity network are trained without explicit supervision. Our formulation enables dense correspondence estimation across views and time, and compelling video editing applications such as motion exaggeration. Our code will be open sourced.

The goal of many computer vision systems is to transform image pixels into 3D representations. Recent popular models use neural networks to regress directly from pixels to 3D object parameters. Such an approach works well when supervision is available, but in problems like human pose and shape estimation, it is difficult to obtain natural images with 3D ground truth. To go one step further, we propose a new architecture that facilitates unsupervised, or lightly supervised, learning. The idea is to break the problem into a series of transformations between increasingly abstract representations. Each step involves a cycle designed to be learnable without annotated training data, and the chain of cycles delivers the final solution. Specifically, we use 2D body part segments as an intermediate representation that contains enough information to be lifted to 3D, and at the same time is simple enough to be learned in an unsupervised way. We demonstrate the method by learning 3D human pose and shape from un-paired and un-annotated images. We also explore varying amounts of paired data and show that cycling greatly alleviates the need for paired data. While we present results for modeling humans, our formulation is general and can be applied to other vision problems.

In this paper, we propose ARCH (Animatable Reconstruction of Clothed Humans), a novel end-to-end framework for accurate reconstruction of animation-ready 3D clothed humans from a monocular image. Existing approaches to digitize 3D humans struggle to handle pose variations and recover details. Also, they do not produce models that are animation ready. In contrast, ARCH is a learned pose-aware model that produces detailed 3D rigged full-body human avatars from a single unconstrained RGB image. A Semantic Space and a Semantic Deformation Field are created using a parametric 3D body estimator. They allow the transformation of 2D/3D clothed humans into a canonical space, reducing ambiguities in geometry caused by pose variations and occlusions in training data. Detailed surface geometry and appearance are learned using an implicit function representation with spatial local features. Furthermore, we propose additional per-pixel supervision on the 3D reconstruction using opacity-aware differentiable rendering. Our experiments indicate that ARCH increases the fidelity of the reconstructed humans. We obtain more than 50% lower reconstruction errors for standard metrics compared to state-of-the-art methods on public datasets. We also show numerous qualitative examples of animated, high-quality reconstructed avatars unseen in the literature so far.

With an increased availability of 3D scanning technology, point clouds are moving into the focus of computer vision as a rich representation of everyday scenes. However, they are hard to handle for machine learning algorithms due to the unordered structure. One common approach is to apply voxelization, which dramatically increases the amount of data stored and at the same time loses details through discretization. Recently, deep learning models with hand-tailored architectures were proposed to handle point clouds directly and achieve input permutation invariance. However, these architectures use an increased number of parameters and are computationally inefficient. In this work we propose basis point sets as a highly efficient and fully general way to process point clouds with machine learning algorithms. Basis point sets are a residual representation that can be computed efficiently and can be used with standard neural network architectures. Using the proposed representation as the input to a relatively simple network allows us to match the performance of PointNet on a shape classification task while using three order of magnitudes less floating point operations. In a second experiment, we show how proposed representation can be used for obtaining high resolution meshes from noisy 3D scans. Here, our network achieves performance comparable to the state-of-the-art computationally intense multi-step frameworks, in one network pass that can be done in less than 1ms.

Direct prediction of 3D body pose and shape remains a challenge even for highly parameterized deep learning models. Mapping from the 2D image space to the prediction space is difficult: perspective ambiguities make the loss function noisy and training data is scarce. In this paper, we propose a novel approach (Neural Body Fitting (NBF)). It integrates a statistical body model within a CNN, leveraging reliable bottom-up semantic body part segmentation and robust top-down body model constraints. NBF is fully differentiable and can be trained using 2D and 3D annotations. In detailed experiments, we analyze how the components of our model affect performance, especially the use ofpart segmentations as an explicit intermediate representation, and present a robust, efficiently trainable framework for 3D human pose estimation from 2D images with competitive results on standard benchmarks. Code will be made available at http://github.com/mohomran/ neural_body_fitting.

3D models provide a common ground for different representations of human bodies. In turn, robust 2D estimation has proven to be a powerful tool to obtain 3D fits in-the-wild. However, depending on the level of detail, it can be hard to impossible to acquire labeled data for training 2D estimators on large scale. We propose a hybrid approach to this problem: with an extended version of the recently introduced SMPLify method, we obtain high quality 3D body model fits for multiple human pose datasets. Human annotators solely sort good and bad fits. This procedure leads to an initial dataset, UP-3D, with rich annotations. With a comprehensive set of experiments, we show how this data can be used to train discriminative models that produce results with an unprecedented level of detail: our models predict 31 segments and 91 landmark locations on the body. Using the 91 landmark pose estimator, we present state-of-the art results for 3D human pose and shape estimation using an order of magnitude less training data and without assumptions about gender or pose in the fitting procedure. We show that UP-3D can be enhanced with these improved fits to grow in quantity and quality, which makes the system deployable on large scale. The data, code and models are available for research purposes.

We present the first image-based generative model of people in clothing for the full body. We sidestep the commonly used complex graphics rendering pipeline and the need for high-quality 3D scans of dressed people. Instead, we learn generative models from a large image database. The main challenge is to cope with the high variance in human pose, shape and appearance. For this reason, pure image-based approaches have not been considered so far. We show that this challenge can be overcome by splitting the generating process in two parts. First, we learn to generate a semantic segmentation of the body and clothing. Second, we learn a conditional model on the resulting segments that creates realistic images. The full model is differentiable and can be conditioned on pose, shape or color. The result are samples of people in different clothing items and styles. The proposed model can generate entirely new people with realistic clothing. In several experiments we present encouraging results that suggest an entirely data-driven approach to people generation is possible.

The caffe framework is one of the leading deep learning toolboxes in the machine learning and computer vision community. While it offers efficiency and configurability, it falls short of a full interface to Python. With increasingly involved procedures for training deep networks and reaching depths of hundreds of layers, creating configuration files and keeping them consistent becomes an error prone process. We introduce the barrista framework, offering full, pythonic control over caffe. It separates responsibilities and offers code to solve frequently occurring tasks for pre-processing, training and model inspection. It is compatible to all caffe versions since mid 2015 and can import and export .prototxt files. Examples are included, e.g., a deep residual network implemented in only 172 lines (for arbitrary depths), comparing to 2320 lines in the official implementation for the equivalent model.

Since the introduction of Random Forests in the 80's they have been a frequently used statistical tool for a variety of machine learning tasks. Many different training algorithms and model adaptions demonstrate the versatility of the forests. This variety resulted in a fragmentation of research and code, since each adaption requires its own algorithms and representations. In 2011, Criminisi and Shotton developed a unifying Decision Forest model for many tasks. By identifying the reusable parts and specifying clear interfaces, we extend this approach to an object oriented representation and implementation. This has the great advantage that research on specific parts of the Decision Forest model can be done 'locally' by reusing well-tested and high-performance components.

The entropy measurement function is a central element of decision forest induction. The Shannon entropy and other generalized entropies such as the Renyi and Tsallis entropy are designed to fulfill the Khinchin-Shannon axioms. Whereas these axioms are appropriate for physical systems, they do not necessarily model well the artificial system of decision forest induction. In this paper, we show that when omitting two of the four axioms, every norm induces an entropy function. The remaining two axioms are sufficient to describe the requirements for an entropy function in the decision forest context. Furthermore, we introduce and analyze the p-norm-induced entropy, show relations to existing entropies and the relation to various heuristics that are commonly used for decision forest training. In experiments with classification, regression and the recently introduced Hough forests, we show how the discrete and differential form of the new entropy can be used for forest induction and how the functions can simply be fine tuned. The experiments indicate that the impact of the entropy function is limited, however can be a simple and useful post-processing step for optimizing decision forests for high performance applications.

Feature learning has the aim to take away the hassle of hand-designing features for machine learning tasks. Since the feature design process is tedious and requires a lot of experience, an automated solution is of great interest. However, an important problem in this field is that usually no objective values are available to fit a feature learning function to. Artificial Neural Networks are a sufficiently flexible tool for function approximation to be able to avoid this problem. We show how the error function of an ANN can be modified such that it works solely with objective distances instead of objective values. We derive the adjusted rules for back propagation through networks with arbitrary depths and include practical considerations that must be taken into account to apply difference based learning successfully. On all three benchmark datasets we use, linear SVMs trained on automatically learned ANN features outperform RBF kernel SVMs trained on the raw data. This can be achieved in a feature space with up to only a tenth of dimensions of the number of original data dimensions. We conclude our work with two experiments on distance based ANN training in two further fields: data visualization and outlier detection.