Search Results

Now showing 1 - 10 of 101
  • Item
    Variational Pose Prediction with Dynamic Sample Selection from Sparse Tracking Signals
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Milef, Nicholas; Sueda, Shinjiro; Kalantari, Nima Khademi; Myszkowski, Karol; Niessner, Matthias
    We propose a learning-based approach for full-body pose reconstruction from extremely sparse upper body tracking data, obtained from a virtual reality (VR) device. We leverage a conditional variational autoencoder with gated recurrent units to synthesize plausible and temporally coherent motions from 4-point tracking (head, hands, and waist positions and orientations). To avoid synthesizing implausible poses, we propose a novel sample selection and interpolation strategy along with an anomaly detection algorithm. Specifically, we monitor the quality of our generated poses using the anomaly detection algorithm and smoothly transition to better samples when the quality falls below a statistically defined threshold. Moreover, we demonstrate that our sample selection and interpolation method can be used for other applications, such as target hitting and collision avoidance, where the generated motions should adhere to the constraints of the virtual environment. Our system is lightweight, operates in real-time, and is able to produce temporally coherent and realistic motions.
  • Item
    Deep Compositional Denoising for High-quality Monte Carlo Rendering
    (The Eurographics Association and John Wiley & Sons Ltd., 2021) Zhang, Xianyao; Manzi, Marco; Vogels, Thijs; Dahlberg, Henrik; Gross, Markus; Papas, Marios; Bousseau, Adrien and McGuire, Morgan
    We propose a deep-learning method for automatically decomposing noisy Monte Carlo renderings into components that kernelpredicting denoisers can denoise more effectively. In our model, a neural decomposition module learns to predict noisy components and corresponding feature maps, which are consecutively reconstructed by a denoising module. The components are predicted based on statistics aggregated at the pixel level by the renderer. Denoising these components individually allows the use of per-component kernels that adapt to each component's noisy signal characteristics. Experimentally, we show that the proposed decomposition module consistently improves the denoising quality of current state-of-the-art kernel-predicting denoisers on large-scale academic and production datasets.
  • Item
    G-Style: Stylized Gaussian Splatting
    (The Eurographics Association and John Wiley & Sons Ltd., 2024) Kovács, Áron Samuel; Hermosilla, Pedro; Raidou, Renata Georgia; Chen, Renjie; Ritschel, Tobias; Whiting, Emily
    We introduce G -Style, a novel algorithm designed to transfer the style of an image onto a 3D scene represented using Gaussian Splatting. Gaussian Splatting is a powerful 3D representation for novel view synthesis, as-compared to other approaches based on Neural Radiance Fields-it provides fast scene renderings and user control over the scene. Recent pre-prints have demonstrated that the style of Gaussian Splatting scenes can be modified using an image exemplar. However, since the scene geometry remains fixed during the stylization process, current solutions fall short of producing satisfactory results. Our algorithm aims to address these limitations by following a three-step process: In a pre-processing step, we remove undesirable Gaussians with large projection areas or highly elongated shapes. Subsequently, we combine several losses carefully designed to preserve different scales of the style in the image, while maintaining as much as possible the integrity of the original scene content. During the stylization process and following the original design of Gaussian Splatting, we split Gaussians where additional detail is necessary within our scene by tracking the gradient of the stylized color. Our experiments demonstrate that G -Style generates high-quality stylizations within just a few minutes, outperforming existing methods both qualitatively and quantitatively
  • Item
    Neural Flow Map Reconstruction
    (The Eurographics Association and John Wiley & Sons Ltd., 2022) Sahoo, Saroj; Lu, Yuzhe; Berger, Matthew; Borgo, Rita; Marai, G. Elisabeta; Schreck, Tobias
    In this paper we present a reconstruction technique for the reduction of unsteady flow data based on neural representations of time-varying vector fields. Our approach is motivated by the large amount of data typically generated in numerical simulations, and in turn the types of data that domain scientists can generate in situ that are compact, yet useful, for post hoc analysis. One type of data commonly acquired during simulation are samples of the flow map, where a single sample is the result of integrating the underlying vector field for a specified time duration. In our work, we treat a collection of flow map samples for a single dataset as a meaningful, compact, and yet incomplete, representation of unsteady flow, and our central objective is to find a representation that enables us to best recover arbitrary flow map samples. To this end, we introduce a technique for learning implicit neural representations of time-varying vector fields that are specifically optimized to reproduce flow map samples sparsely covering the spatiotemporal domain of the data. We show that, despite aggressive data reduction, our optimization problem - learning a function-space neural network to reproduce flow map samples under a fixed integration scheme - leads to representations that demonstrate strong generalization, both in the field itself, and using the field to approximate the flow map. Through quantitative and qualitative analysis across different datasets we show that our approach is an improvement across a variety of data reduction methods, and across a variety of measures ranging from improved vector fields, flow maps, and features derived from the flow map.
  • Item
    NEnv: Neural Environment Maps for Global Illumination
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Rodriguez-Pardo, Carlos; Fabre, Javier; Garces, Elena; Lopez-Moreno, Jorge; Ritschel, Tobias; Weidlich, Andrea
    Environment maps are commonly used to represent and compute far-field illumination in virtual scenes. However, they are expensive to evaluate and sample from, limiting their applicability to real-time rendering. Previous methods have focused on compression through spherical-domain approximations, or on learning priors for natural, day-light illumination. These hinder both accuracy and generality, and do not provide the probability information required for importance-sampling Monte Carlo integration. We propose NEnv, a deep-learning fully-differentiable method, capable of compressing and learning to sample from a single environment map. NEnv is composed of two different neural networks: A normalizing flow, able to map samples from uniform distributions to the probability density of the illumination, also providing their corresponding probabilities; and an implicit neural representation which compresses the environment map into an efficient differentiable function. The computation time of environment samples with NEnv is two orders of magnitude less than with traditional methods. NEnv makes no assumptions regarding the content (i.e. natural illumination), thus achieving higher generality than previous learning-based approaches. We share our implementation and a diverse dataset of trained neural environment maps, which can be easily integrated into existing rendering engines.
  • Item
    Deep Fluids: A Generative Network for Parameterized Fluid Simulations
    (The Eurographics Association and John Wiley & Sons Ltd., 2019) Kim, Byungsoo; Azevedo, Vinicius C.; Thuerey, Nils; Kim, Theodore; Gross, Markus; Solenthaler, Barbara; Alliez, Pierre and Pellacini, Fabio
    This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters. A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields. Due to the capability of deep learning architectures to learn representative features of the data, our generative model is able to accurately approximate the training data set, while providing plausible interpolated in-betweens. The proposed generative model is optimized for fluids by a novel loss function that guarantees divergence-free velocity fields at all times. In addition, we demonstrate that we can handle complex parameterizations in reduced spaces, and advance simulations in time by integrating in the latent space with a second network. Our method models a wide variety of fluid behaviors, thus enabling applications such as fast construction of simulations, interpolation of fluids with different parameters, time re-sampling, latent space simulations, and compression of fluid simulation data. Reconstructed velocity fields are generated up to 700x faster than re-simulating the data with the underlying CPU solver, while achieving compression rates of up to 1300x.
  • Item
    Write Like You: Synthesizing Your Cursive Online Chinese Handwriting via Metric-based Meta Learning
    (The Eurographics Association and John Wiley & Sons Ltd., 2021) Tang, Shusen; Lian, Zhouhui; Mitra, Niloy and Viola, Ivan
    In this paper, we propose a novel Sequence-to-Sequence model based on metric-based meta learning for the arbitrary style transfer of online Chinese handwritings. Unlike most existing methods that treat Chinese handwritings as images and are unable to reflect the human writing process, the proposed model directly handles sequential online Chinese handwritings. Generally, our model consists of three sub-models: a content encoder, a style encoder and a decoder, which are all Recurrent Neural Networks. In order to adaptively obtain the style information, we introduce an attention-based adaptive style block which has been experimentally proven to bring considerable improvement to our model. In addition, to disentangle the latent style information from characters written by any writers effectively, we adopt metric-based meta learning and pre-train the style encoder using a carefully-designed discriminative loss function. Then, our entire model is trained in an end-to-end manner and the decoder adaptively receives the style information from the style encoder and the content information from the content encoder to synthesize the target output. Finally, by feeding the trained model with a content character and several characters written by a given user, our model can write that Chinese character in the user's handwriting style by drawing strokes one by one like humans. That is to say, as long as you write several Chinese character samples, our model can imitate your handwriting style when writing. In addition, after fine-tuning the model with a few samples, it can generate more realistic handwritings that are difficult to be distinguished from the real ones. Both qualitative and quantitative experiments demonstrate the effectiveness and superiority of our method.
  • Item
    Face Editing Using Part-Based Optimization of the Latent Space
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Aliari, Mohammad Amin; Beauchamp, Andre; Popa, Tiberiu; Paquette, Eric; Myszkowski, Karol; Niessner, Matthias
    We propose an approach for interactive 3D face editing based on deep generative models. Most of the current face modeling methods rely on linear methods and cannot express complex and non-linear deformations. In contrast to 3D morphable face models based on Principal Component Analysis (PCA), we introduce a novel architecture based on variational autoencoders. Our architecture has multiple encoders (one for each part of the face, such as the nose and mouth) which feed a single decoder. As a result, each sub-vector of the latent vector represents one part. We train our model with a novel loss function that further disentangles the space based on different parts of the face. The output of the network is a whole 3D face. Hence, unlike partbased PCA methods, our model learns to merge the parts intrinsically and does not require an additional merging process. To achieve interactive face modeling, we optimize for the latent variables given vertex positional constraints provided by a user. To avoid unwanted global changes elsewhere on the face, we only optimize the subset of the latent vector that corresponds to the part of the face being modified. Our editing optimization converges in less than a second. Our results show that the proposed approach supports a broader range of editing constraints and generates more realistic 3D faces.
  • Item
    Cross-Shape Attention for Part Segmentation of 3D Point Clouds
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Loizou, Marios; Garg, Siddhant; Petrov, Dmitry; Averkiou, Melinos; Kalogerakis, Evangelos; Memari, Pooran; Solomon, Justin
    We present a deep learning method that propagates point-wise feature representations across shapes within a collection for the purpose of 3D shape segmentation. We propose a cross-shape attention mechanism to enable interactions between a shape's point-wise features and those of other shapes. The mechanism assesses both the degree of interaction between points and also mediates feature propagation across shapes, improving the accuracy and consistency of the resulting point-wise feature representations for shape segmentation. Our method also proposes a shape retrieval measure to select suitable shapes for crossshape attention operations for each test shape. Our experiments demonstrate that our approach yields state-of-the-art results in the popular PartNet dataset.
  • Item
    Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow
    (The Eurographics Association and John Wiley & Sons Ltd., 2020) Wiewel, Steffen; Kim, Byungsoo; Azevedo, Vinicius; Solenthaler, Barbara; Thuerey, Nils; Bender, Jan and Popa, Tiberiu
    We propose an end-to-end trained neural network architecture to robustly predict the complex dynamics of fluid flows with high temporal stability. We focus on single-phase smoke simulations in 2D and 3D based on the incompressible Navier-Stokes (NS) equations, which are relevant for a wide range of practical problems. To achieve stable predictions for long-term flow sequences with linear execution times, a convolutional neural network (CNN) is trained for spatial compression in combination with a temporal prediction network that consists of stacked Long Short-Term Memory (LSTM) layers. Our core contribution is a novel latent space subdivision (LSS) to separate the respective input quantities into individual parts of the encoded latent space domain. As a result, this allows to distinctively alter the encoded quantities without interfering with the remaining latent space values and hence maximizes external control. By selectively overwriting parts of the predicted latent space points, our proposed method is capable to robustly predict long-term sequences of complex physics problems, like the flow of fluids. In addition, we highlight the benefits of a recurrent training on the latent space creation, which is performed by the spatial compression network. Furthermore, we thoroughly evaluate and discuss several different components of our method.