Recent advances in Sign Language Production (SLP) highlight denoising diffusion models as promising alternatives to traditional autoregressive methods. Most existing approaches follow a two-stage pipeline that encodes sign motion into discrete latent codes, often sacrificing Space–Time fidelity and requiring gloss annotations or complex codebooks. Transformer-based models aim to simplify this, but often produce overly smooth, unnatural motions. We introduce Sign Language Production with Scale-Aware Modulation (SignSAM), a novel single-stage, gloss-free SLP framework that directly synthesizes motion in continuous space, preserving fine temporal details. At its core is a Space–Time U-Net that learns compact temporal features by jointly downscaling the frame and sign feature dimensions, thereby reducing computational cost compared to a no-pyramid UNet or a pyramid UNet without consistency between dimensions. To further enhance temporal precision, we propose a Timing Scale-Aware Modulation module that fuses multiscale temporal resolutions for better motion coherence. Experiments on PHOENIX14T and How2Sign show that SignSAM achieves state-of-the-art (SOTA) fluency, accuracy, and naturalness, offering an efficient and expressive solution for SLP. Our project homepage is https://kha-kim-thuy.github.io/SLP-Demo/ .

The explosive or volcanic scenes in motion pictures involve complex turbulent flow as its temperature and density vary in space. To simulate this turbulent flow of an inhomogeneous fluid, we propose a simple and efficient framework. Instead of explicitly computing the complex motion of this fluid dynamical instability, we first approximate the average motion of the fluid. Then, the high-resolution dynamics is computed using our new extended version of the vortex particle method with baroclinity. This baroclinity term makes turbulent effects by generating new vortex particles according to temperature/density distributions. Using our method, we efficiently simulated a complex scene with varying density and temperature.

In this paper, we propose a simple and efficient framework for simulating dispersed bubble flow. Instead of modeling the complex hydrodynamics of numerous small bubbles explicitly, our method approximates the average motion of these bubbles using a continuum multiphase solver. Then, the subgrid interactions among bubbles are computed using our new stochastic solver. Using the proposed scheme, we can efficiently simulate complex scenes with millions of bubbles.

This paper presents a novel framework for simulating the stretching and wiggling of liquids. We demonstrate that complex phase-interface dynamics can be effectively simulated by introducing the Eulerian vortex sheet method, which focuses on the vorticity at the interface (rather than the whole domain). We extend this model to provide user control for the production of visual effects. Then, the generated fluid flow creates complex surface details, such as thin and wiggling fluid sheets. To capture such high-frequency features efficiently, this work employs a denser grid for surface tracking in addition to the (coarser) simulation grid. In this context, the paper proposes a filter, called the liquid-biased filter, which is able to downsample the surface in the high-resolution grid into the coarse grid without unrealistic volume loss resulting from aliasing error. The proposed method, which runs on a single PC, realistically reproduces complex fluid scenes.

Abstract In this paper, we propose a new constrained interpolation profile (CIP) method that is stable and accurate but requires less amount of computation compared to existing CIP‐based solvers. CIP is a high‐order fluid advection solver that can reproduce rich details of fluids. It has third‐order accuracy but its computation is performed over a compact stencil. These advantageous features of CIP are, however, diluted by the following two shortcomings: (1) CIP contains a defect in the utilization of the grid data, which makes the method suitable only for simulations with a tight CFL restriction; and (2) CIP does not guarantee unconditional stability. There have been several attempts to fix these problems in CIP, but they have been only partially successful. The solutions that fixed both problems ended up introducing other undesirable features, namely increased computation time and/or reduced accuracy. This paper proposes a novel modification of the original CIP method that fixes all of the above problems without increasing the computational load or reducing the accuracy. Both quantitative and visual experiments were performed to test the performance of the new CIP in comparison to existing fluid solvers. The results show that the proposed method brings significant improvements in both accuracy and speed.

We present a new fluid simulation technique that significantly reduces the nonphysical dissipation of velocity. The proposed method is based on an apt use of particles and derivative information. We note that a major source of numerical dissipation in the conventional Navier-Stokes equations solver lies in the advection step. Hence, starting with the conventional grid-based simulator, when the details of fluid movements need to be simulated, we replace the advection part with a particle simulator. When swapping between the grid-based and particle-based simulators, the physical quantities such as the level set and velocity must be converted. For this purpose, we develop a novel dissipation-suppressing conversion procedure that utilizes the derivative information stored in the particles, as well as in the grid points. For the fluid regions where such details are not needed, the advection is simulated using an octree-based constrained interpolation profile (CIP) solver, which we develop in this work. Through several experiments, we show that the proposed technique can reproduce the detailed movements of high-Reynolds-number fluids such as droplets/bubbles, thin water sheets, and whirlpools. The increased accuracy in the advection, which forms the basis of the proposed technique, can also be used to produce better results in larger scale fluid simulations.

This article presents a physically-based technique for simulating water. This work is motivated by the "stable fluids" method, developed by Stam [1999], to handle gaseous fluids. We extend this technique to water, which calls for the development of methods for modeling multiphase fluids and suppressing dissipation. We construct a multiphase fluid formulation by combining the Navier--Stokes equations with the level set method. By adopting constrained interpolation profile (CIP)-based advection, we reduce the numerical dissipation and diffusion significantly. We further reduce the dissipation by converting potentially dissipative cells into droplets or bubbles that undergo Lagrangian motion. Due to the multiphase formulation, the proposed method properly simulates the interaction of water with surrounding air, instead of simulating water in a void space. Moreover, the introduction of the nondissipative technique means that, in contrast to previous methods, the simulated water does not unnecessarily lose mass, and its motion is not damped to an unphysical extent. Experiments showed that the proposed method is stable and runs fast. It is demonstrated that two-dimensional simulation runs in real-time.

This paper presents a new method for editing an existing motion to satisfy a set of user-specified constraints, and in doing so guaranteeing the kinematic and dynamic soundness of the transformed motion. We cast the motion editing problem as a constrained state estimation problem based on the per-frame Kalman filter framework. To handle various kinds of kinematic and dynamic constraints in a scalable fashion, we develop a new algorithm, called spacetime sweeping, which sweeps through the frames with two consecutive filters. The unscented Kalman (UK) filter estimates an optimal pose for the current frame that conforms to the given constraints, and feeds the result to the least-squares (LS) filter. Then, the LS filter resolves the inter-frame inconsistencies introduced by the UK filter due to the independent handling of the position, velocity and acceleration. The per-frame approach of the space-time sweeping provides a surprising performance gain. Thus editing of motion that involves dynamic constraints, such as dynamic balancing, can be done interactively.

This paper presents a new technique called motion balance filtering, which corrects an unbalanced motion to a balanced one while preserving the original motion characteristics as much as possible. Differently from previous approaches that deal only with the balance of static posture, we solve the problem of balancing a dynamic motion. We achieve dynamic balance by analyzing and controlling the trajectory of the zero moment point (ZMP). Our algorithm consists of three steps. First, it analyzes the ZMP trajectory to find out the duration in which dynamic balance is violated. Dynamic imbalance is identified by the ZMP trajectory segments lying out of the supporting area. Next, the algorithm modifies the ZMP trajectory by projecting it into the supporting area. Finally, it generates the balanced motion that satisfies the new ZMP constraint. This process is formulated as a constrained optimization problem so that the new motion resembles the original motion as much as possible. Experiments prove that our motion balance filtering algorithm is a useful method to add physical realism to a kinematically edited motion.