共找到 20 条结果
Modern commercial games are designed for mass appeal, not for individual players, but there is a unique opportunity in video games to better fit the individual through adapting game elements. In this paper, we focus on AI Directors, systems which can dynamically modify a game, that personalize the player experience to match the player's preference. In the past, some AI Director studies have provided inconclusive results, so their effect on player experience is not clear. We take three AI Directors and directly compare them in a human subject study to test their effectiveness on quest selection. Our results show that a non-random AI Director provides a better player experience than a random AI Director.
The effect of higher order continuity in the solution field by using NURBS basis function in isogeometric analysis (IGA) is investigated for an efficient mixed finite element formulation for elastostatic beams. It is based on the Hu-Washizu variational principle considering geometrical and material nonlinearities. Here we present a reduced degree of basis functions for the additional fields of the stress resultants and strains of the beam, which are allowed to be discontinuous across elements. This approach turns out to significantly improve the computational efficiency and the accuracy of the results. We consider a beam formulation with extensible directors, where cross-sectional strains are enriched to avoid Poisson locking by an enhanced assumed strain method. In numerical examples, we show the superior per degree-of-freedom accuracy of IGA over conventional finite element analysis, due to the higher order continuity in the displacement field. We further verify the efficient rotational coupling between beams, as well as the path-independence of the results.
In the paradigm of AI-generated content (AIGC), there has been increasing attention to transferring knowledge from pre-trained text-to-image (T2I) models to text-to-video (T2V) generation. Despite their effectiveness, these frameworks face challenges in maintaining consistent narratives and handling shifts in scene composition or object placement from a single abstract user prompt. Exploring the ability of large language models (LLMs) to generate time-dependent, frame-by-frame prompts, this paper introduces a new framework, dubbed DirecT2V. DirecT2V leverages instruction-tuned LLMs as directors, enabling the inclusion of time-varying content and facilitating consistent video generation. To maintain temporal consistency and prevent mapping the value to a different object, we equip a diffusion model with a novel value mapping method and dual-softmax filtering, which do not require any additional training. The experimental results validate the effectiveness of our framework in producing visually coherent and storyful videos from abstract user prompts, successfully addressing the challenges of zero-shot video generation.
Cutscenes form an integral part of many video games, but their creation is costly, time-consuming, and requires skills that many game developers lack. While AI has been leveraged to semi-automate cutscene production, the results typically lack the internal consistency and uniformity in style that is characteristic of professional human directors. We overcome this shortcoming with Cine-AI, an open-source procedural cinematography toolset capable of generating in-game cutscenes in the style of eminent human directors. Implemented in the popular game engine Unity, Cine-AI features a novel timeline and storyboard interface for design-time manipulation, combined with runtime cinematography automation. Via two user studies, each employing quantitative and qualitative measures, we demonstrate that Cine-AI generates cutscenes that people correctly associate with a target director, while providing above-average usability. Our director imitation dataset is publicly available, and can be extended by users and film enthusiasts.
This paper presents an isogeometric finite element formulation for nonlinear beams with impenetrability constraints, based on the kinematics of Cosserat rods with unconstrained directors. The beam cross-sectional deformation is represented by director vectors of an arbitrary order. For the frictionless lateral beam-to-beam contact, a surface-to-surface contact algorithm combined with an active set strategy and a penalty method is employed. The lateral boundary surface of the beam is parameterized by its axis and cross-sectional boundary curves with NURBS basis functions having at least $C^2$-continuity, which yields a continuous surface metric and curvature for the closest point projection. Three-dimensional constitutive laws of hyperelastic materials are considered. Several numerical examples verify the accuracy and efficiency of the proposed beam contact formulation in comparison to brick element solutions. The lateral contact pressure distribution of the beam formulation is in excellent agreement with the contact pressure of the brick element formulation while requiring much less degrees-of-freedom.
We study the networks formed by the directors of the most important Swiss boards and the boards themselves for the year 2009. The networks are obtained by projection from the original bipartite graph. We highlight a number of important statistical features of those networks such as degree distribution, weight distribution, and several centrality measures as well as their interrelationships. While similar statistics were already known for other board systems, and are comparable here, we have extended the study with a careful investigation of director and board centrality, a k-core analysis, and a simulation of the speed of information propagation and its relationships with the topological aspects of the network such as clustering and link weight and betweenness. The overall picture that emerges is one in which the topological structure of the Swiss board and director networks has evolved in such a way that special actors and links between actors play a fundamental role in the flow of information among distant parts of the network. This is shown in particular by the centrality measures and by the simulation of a simple epidemic process on the directors network.
In many countries, the representation of women on corporate boards of directors has become a topic of intense political debate. Social networking plays a crucial role in the appointment to a board so that an informed debate requires knowing where women are located in the network of directors. One way to quantify the network is by studying the links created by serving on the same board and by joint appointments on multiple boards. We analyse a network of $\approx 320\,000$ board members of $36\,000$ companies traded on stock exchanges all over the world, focusing specifically on the position of women in the network. Women only have $\approx 9-13\%$ of all seats, but they are not marginalised. Applying metrics from social network analysis, we find that their influence is close to that of men. We do not find evidence to support previous claims that women play the role of "queen bees" that exclude other women from similar positions.
We examine the spatial field of orientations of slender fibers that are advected by a two-dimensional fluid flow. The orientation field of these passive directors are important in a wide range of industrial and geophysical flows. We introduce emergent scar lines as the dominant coherent structures in the orientation field of passive directors in chaotic flows. Previous work has identified the existence of scar lines where the orientation rotates by π over short distances, but the lines that were identified disappeared as time progressed. As a result, earlier work focused on topological singularities in the orientation field which we find to play a negligible role at long times. We use the standard map as a simple time-periodic two-dimensional (2D) flow that produces Lagrangian chaos. This class of flows produce persistent patterns in passive scalar advection, and we find that a different kind of persistent pattern develops in the passive director orientation field. We identify the mechanism by which emergent scar lines grow to dominate these patterns at long times in complex flows. Emergent scar lines form where the recent stretching of the fluid element is perpendicular to earlier
A triangulated spherical surface model is numerically studied, and it is shown that the model undergoes phase transitions between the smooth phase and the collapsed phase. The model is defined by using a director field, which is assumed to have an interaction with a normal of the surface. The interaction between the directors and the surface maintains the surface shape. The director field is not defined within the two-dimensional differential geometry, and this is in sharp contrast to the conventional surface models, where the surface shape is maintained only by the curvature energies. We also show that the interaction makes the Nambu-Goto model well-defined, where the bond potential is given by the area of triangles; the Nambu-Goto model is well-known as an ill-defined one even when the conventional two-dimensional bending energy is included in the Hamiltonian.
In experiments and numerical simulations we measured angles between the symmetry axes of small spheroids advected in turbulence ("passive directors"). Since turbulent strains tend to align nearby spheroids, one might think that their relative angles are quite small. We show that this intuition fails in general because angles between the symmetry axes of nearby particles are anomalously large. We identify two mechanisms that cause this phenomenon. First, the dynamics evolves to a fractal attractor despite the fact that the fluid velocity is spatially smooth at small scales. Second, this fractal forms steps akin to scar lines observed in the director patterns for random or chaotic two-dimensional maps.
Interlocking directorships-where individuals simultaneously serve on the boards of multiple corporations-can facilitate the exchange of expertise and strategic alignment but also present risks, including conflicts of interest, economic 'oligarchy', and regulatory non-compliance. In contexts such as large, family-controlled corporate conglomerates in India, the manual detection of interlocks is hindered by the high volume of corporate entities and the complex involvement of extended familial networks. This study introduces a scalable, graph-theoretic framework for the systematic identification and analysis of interlocking directorships. Using Breadth-First Search (BFS) traversal, we examined a curated dataset comprising over 50,000 directors, 85,000 companies, and 300,000 director-company affiliations, yielding a comprehensive representation of corporate network structures. Large Language Models (LLMs) were integrated into the analytical pipeline to characterize both personal and professional linkages among directors. Empirical results indicate that 17% of directors hold positions in exactly two companies, while 58.6% maintain directorships in two or more companies. The combined BFS
While diffusion models generate high-fidelity video clips, transforming them into coherent storytelling engines remains challenging. Current agentic pipelines automate this via chained modules but suffer from semantic drift and cascading failures due to independent, handcrafted prompting. We present Co-Director, a hierarchical multi-agent framework formalizing video storytelling as a global optimization problem. To ensure semantic coherence, we introduce hierarchical parameterization: a multi-armed bandit globally identifies promising creative directions, while a local multimodal self-refinement loop mitigates identity drift and ensures sequence-level consistency. This balances the exploration of novel narrative strategies with the exploitation of effective creative configurations. For evaluation, we introduce GenAD-Bench, a 400-scenario dataset of fictional products for personalized advertising. Experiments demonstrate that Co-Director significantly outperforms state-of-the-art baselines, offering a principled approach that seamlessly generalizes to broader cinematic narratives. Project Page: https://co-director-agent.github.io/
Effective communication between directors and cinematographers is fundamental in film production, yet traditional approaches relying on visual references and hand-drawn storyboards often lack the efficiency and precision necessary during pre-production. We present CineVision, an AI-driven platform that integrates scriptwriting with real-time visual pre-visualization to bridge this communication gap. By offering dynamic lighting control, style emulation based on renowned filmmakers, and customizable character design, CineVision enables directors to convey their creative vision with heightened clarity and rapidly iterate on scene composition. In a 24-participant lab study, CineVision yielded shorter task times and higher usability ratings than two baseline methods, suggesting a potential to ease early-stage communication and accelerate storyboard drafts under controlled conditions. These findings underscore CineVision's potential to streamline pre-production processes and foster deeper creative synergy among filmmaking teams, particularly for new collaborators. Our code and demo are available at https://github.com/TonyHongtaoWu/CineVision.
Camera trajectory design plays a crucial role in video production, serving as a fundamental tool for conveying directorial intent and enhancing visual storytelling. In cinematography, Directors of Photography meticulously craft camera movements to achieve expressive and intentional framing. However, existing methods for camera trajectory generation remain limited: Traditional approaches rely on geometric optimization or handcrafted procedural systems, while recent learning-based methods often inherit structural biases or lack textual alignment, constraining creative synthesis. In this work, we introduce an auto-regressive model inspired by the expertise of Directors of Photography to generate artistic and expressive camera trajectories. We first introduce DataDoP, a large-scale multi-modal dataset containing 29K real-world shots with free-moving camera trajectories, depth maps, and detailed captions in specific movements, interaction with the scene, and directorial intent. Thanks to the comprehensive and diverse database, we further train an auto-regressive, decoder-only Transformer for high-quality, context-aware camera movement generation based on text guidance and RGBD inputs, n
We present Mind-of-Director, a multi-modal agent-driven framework for film previz that models the collaborative decision-making process of a film production team. Given a creative idea, Mind-of-Director orchestrates multiple specialized agents to produce previz sequences within the game engine. The framework consists of four cooperative modules: Script Development, where agents draft and refine the screenplay iteratively; Virtual Scene Design, which transforms text into semantically aligned 3D environments; Character Behaviour Control, which determines character blocking and motion; and Camera Planning, which optimizes framing, movement, and composition for cinematic camera effects. A real-time visual editing system built in the game engine further enables interactive inspection and synchronized timeline adjustment across scenes, behaviours, and cameras. Extensive experiments and human evaluations show that Mind-of-Director generates high-quality, semantically grounded previz sequences in approximately 25 minutes per idea, demonstrating the effectiveness of agent collaboration for both automated prototyping and human-in-the-loop filmmaking.
The automatic movie dubbing model generates vivid speech from given scripts, replicating a speaker's timbre from a brief timbre prompt while ensuring lip-sync with the silent video. Existing approaches simulate a simplified workflow where actors dub directly without preparation, overlooking the critical director-actor interaction. In contrast, authentic workflows involve a dynamic collaboration: directors actively engage with actors, guiding them to internalize the context cues, specifically emotion, before performance. To address this issue, we propose a new Retrieve-Augmented Director-Actor Interaction Learning scheme to achieve authentic movie dubbing, termed Authentic-Dubber, which contains three novel mechanisms: (1) We construct a multimodal Reference Footage library to simulate the learning footage provided by directors. Note that we integrate Large Language Models (LLMs) to achieve deep comprehension of emotional representations across multimodal signals. (2) To emulate how actors efficiently and comprehensively internalize director-provided footage during dubbing, we propose an Emotion-Similarity-based Retrieval-Augmentation strategy. This strategy retrieves the most relev
This project is a collaboration between industry and academia to delve into Finance Social Networks, specifically the Board of Directors of public companies. Knowing the connections between Directors and Executives in different companies can generate powerful stories and meaningful insights on investments. A proof of concept in the form of a Data Visualization tool reveals its strength in investigating corporate governance and sustainability, as well as in the partnership between industry and academic institutions.
A dynamic light scattering study of director-layer fluctuations in the antiferroelectric smectic-ZA phase of the ferroelectric nematic liquid crystal DIO is reported. The dynamics are consistent with the distinctive feature of the ZA phase that the smectic layers form parallel to the axis of molecular orientational order (director). A model is developed to describe quantitatively the dispersion of the fluctuation relaxation rates. The model is based on a specialization of the elastic free energy density of the smectic-C phase to the case of 90 degree director tilt, a "first-order" approximation of the viscous stresses by their form for an incompressible uniaxial fluid, and a treatment of the effect of chevron layer structure that develops in planar sample cells due to temperature-dependent layer shrinkage, as documented in previous studies on DIO. From the modeling, the layer compression elastic constant is estimated to be ~100 times lower in the smectic-ZA phase than in an ordinary smectic-A liquid crystal. Possible effects of the antiferroelectric layer polarization on the director splay elasticity and viscosity are described. The temperature dependencies of the splay, twist, and
We merge classical origami concepts with active actuation by designing origami patterns whose panels undergo prescribed metric changes. These metric changes render the system non-Euclidean, inducing non-zero Gaussian curvature at the vertices after actuation. Such patterns can be realized by programming piecewise constant director fields in liquid crystal elastomer (LCE) sheets. In this work, we address the geometric design of both compatible reference director patterns and their corresponding actuated configurations. On the reference configuration, we systematically construct director patterns that satisfy metric compatibility across interfaces. We prove the existence and uniqueness of compatible director fields at a vertex for the generic case, up to orthogonal duals. The Gaussian curvature of the actuated vertex is computed based on the compatible director fields. On the actuated configuration, we develop a continuum mechanics framework to analyze the kinematics of non-Euclidean origami. In particular, we fully characterize the deformation spaces of three-fold and four-fold vertices and establish analytical relationships between their deformations and the director patterns. Buil
The Explorer-Director game, first introduced by Nedev and Muthukrishnan (2008), simulates a Mobile Agent exploring a ring network with an inconsistent global sense of direction. Two players, the Explorer and the Director, jointly control a token's movement on the vertices of a graph $G$ with initial location $v$. Each turn, the Explorer calls any valid distance, $d$, aiming to maximize the number of vertices the token visits, and the Director moves the token to any vertex distance $d$ away aiming to minimize the number of visited vertices. The game ends when no new vertices can be visited, assuming optimal play, and we denote the total number of visited vertices by $f_d(G,v)$. Here we study a variant where, if the token is on vertex $u$, the Explorer is allowed to select any valid \emph{path length}, $\ell$, and the Director now moves the token to any vertex $v$ such that $G$ contains a $uv$ path of length $\ell$. The corresponding parameter is $f_p(G,v)$. In this paper, we explore how far apart $f_d(G,v)$ and $f_p(G,v)$ can be, proving that for any $n$ there are graphs $G$ and $H$ with $f_p(G,v)-f_d(G,v)>n$ and $f_d(H,v)-f_p(H,v)>n$.