Search

We propose a novel methodology to enhance grid-based fluid animation with pointwise divergence-free velocity interpolation. Our method takes as input a discretely divergence-free staggered grid velocity field generated by a standard pressure projection, and first recovers a consistent corresponding edge-based discrete vector potential in 3D (or node-based stream function in 2D). We interpolate these values to form a pointwise potential, and apply the continuous curl operator to recover a pointwise flow field that is perfectly incompressible. Our method supports irregular geometry through the use of level set-based cut-cells. To recover a smooth and velocity-consistent discrete vector potential in 3D, we employ a sweeping approach followed by a gauge correction that requires a single scalar Poisson solve, rather than a vector Poisson problem. In both 2D and 3D, we show how modified interpolation strategies can be applied to better account for the presence of irregular cut-cell boundaries. Our results demonstrate that our overall proposed Curl-Flow framework produces significantly better particle trajectories that suffer from far fewer spurious sources or sinks, respect irregular obstacles, and better preserve particle distributions over time.

Artistically controlling the shape, motion and appearance of fluid simulations pose major challenges in visual effects production. In this paper, we present a neural style transfer approach from images to 3D fluids formulated in a Lagrangian viewpoint. Using particles for style transfer has unique benefits compared to grid-based techniques. Attributes are stored on the particles and hence are trivially transported by the particle motion. This intrinsically ensures temporal consistency of the optimized stylized structure and notably improves the resulting quality. Simultaneously, the expensive, recursive alignment of stylization velocity fields of grid approaches is unnecessary, reducing the computation time to less than an hour and rendering neural flow stylization practical in production settings. Moreover, the Lagrangian representation improves artistic control as it allows for multi-fluid stylization and consistent color transfer from images, and the generality of the method enables stylization of smoke and liquids likewise., Comment: ACM Transaction on Graphics (SIGGRAPH 2020), additional materials: http://www.byungsoo.me/project/lnst/index.html

We propose an end-to-end trained neural networkarchitecture 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, 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. 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. In addition, we highlight the benefits of a recurrent training on the latent space creation, which is performed by the spatial compression network., Comment: https://ge.in.tum.de/publications/latent-space-subdivision/

Artistically controlling fluid simulations requires a large amount of manual work by an artist. The recently presented transportbased neural style transfer approach simplifies workflows as it transfers the style of arbitrary input images onto 3D smoke simulations. However, the method only modifies the shape of the fluid but omits color information. In this work, we therefore extend the previous approach to obtain a complete pipeline for transferring shape and color information onto 2D and 3D smoke simulations with neural networks. Our results demonstrate that our method successfully transfers colored style features consistently in space and time to smoke data for different input textures., Comment: Submitted to Eurographics2020

Convolutional neural networks were recently employed to fully reconstruct fluid simulation data from a set of reduced parameters. However, since (de-)convolutions traditionally trained with supervised L1-loss functions do not discriminate between low and high frequencies in the data, the error is not minimized efficiently for higher bands. This directly correlates with the quality of the perceived results, since missing high frequency details are easily noticeable. In this paper, we analyze the reconstruction quality of generative networks and present a frequency-aware loss function that is able to focus on specific bands of the dataset during training time. We show that our approach improves reconstruction quality of fluid simulation data in mid-frequency bands, yielding perceptually better results while requiring comparable training time., Comment: Submitted to Eurographics2020

Artistically controlling fluids has always been a challenging task. Optimization techniques rely on approximating simulation states towards target velocity or density field configurations, which are often handcrafted by artists to indirectly control smoke dynamics. Patch synthesis techniques transfer image textures or simulation features to a target flow field. However, these are either limited to adding structural patterns or augmenting coarse flows with turbulent structures, and hence cannot capture the full spectrum of different styles and semantically complex structures. In this paper, we propose the first Transport-based Neural Style Transfer (TNST) algorithm for volumetric smoke data. Our method is able to transfer features from natural images to smoke simulations, enabling general content-aware manipulations ranging from simple patterns to intricate motifs. The proposed algorithm is physically inspired, since it computes the density transport from a source input smoke to a desired target configuration. Our transport-based approach allows direct control over the divergence of the stylization velocity field by optimizing incompressible and irrotational potentials that transport smoke towards stylization. Temporal consistency is ensured by transporting and aligning subsequent stylized velocities, and 3D reconstructions are computed by seamlessly merging stylizations from different camera viewpoints., Comment: ACM Transaction on Graphics (SIGGRAPH ASIA 2019), additional materials: http://www.byungsoo.me/project/neural-flow-style

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., Comment: Computer Graphics Forum (Proceedings of EUROGRAPHICS 2019), additional materials: http://www.byungsoo.me/project/deep-fluids/