Visual Effects Production Research Articles

Computer-Aided Film Visual Effects Production Based on Class Activation Mapping

Computer-Aided Film Visual Effects Production Based on Class Activation Mapping

Neural Denoising for Deep‐Z Monte Carlo Renderings

AbstractWe present a kernel‐predicting neural denoising method for path‐traced deep‐Z images that facilitates their usage in animation and visual effects production. Deep‐Z images provide enhanced flexibility during compositing as they contain color, opacity, and other rendered data at multiple depth‐resolved bins within each pixel. However, they are subject to noise, and rendering until convergence is prohibitively expensive. The current state of the art in deep‐Z denoising yields objectionable artifacts, and current neural denoising methods are incapable of handling the variable number of depth bins in deep‐Z images. Our method extends kernel‐predicting convolutional neural networks to address the challenges stemming from denoising deep‐Z images. We propose a hybrid reconstruction architecture that combines the depth‐resolved reconstruction at each bin with the flattened reconstruction at the pixel level. Moreover, we propose depth‐aware neighbor indexing of the depth‐resolved inputs to the convolution and denoising kernel application operators, which reduces artifacts caused by depth misalignment present in deep‐Z images. We evaluate our method on a production‐quality deep‐Z dataset, demonstrating significant improvements in denoising quality and performance compared to the current state‐of‐the‐art deep‐Z denoiser. By addressing the significant challenge of the cost associated with rendering path‐traced deep‐Z images, we believe that our approach will pave the way for broader adoption of deep‐Z workflows in future productions.

Fault-Tolerance and Reliability for Dependable Systems

In this analysis, we look into the factors that contribute to fault-tolerance and dependability in operational systems. Visual effects production and post-production processes rely significantly on technology and automation, making reliable systems essential to the operation of the industry. In order to improve system performance and dependability, this research examines the existing literature on fault-tolerance and reliability for dependable systems and identifies numerous strategies, techniques, and approaches. In order to guarantee the dependability of complex systems, the study concludes that fault-tolerant control systems, redundancy-based approaches, adaptive control methods, consensus algorithms, and failure detection algorithms are essential. Model-based approaches, fault-tree analysis, and Markov models are all highlighted as crucial to the examination of system dependability in this paper. The findings of this study have considerable consequences for the domains of visual effects and related disciplines, as they provide valuable insights and recommendations for enhancing the dependability and performance of such systems. The study concludes with several recommendations for further study, including the creation of new fault-tolerant algorithms, the examination of system reliability in a variety of contexts, and the incorporation of machine learning and AI into such systems.

Physics-Based Combustion Simulation

We propose a physics-based combustion simulation method for computer graphics that extends the mathematical models of previous efforts to automatically capture more realistic flames as well as temperature and soot distributions. Our method includes mathematical models for the thermodynamic properties of real-world fuels which enables, for example, the prediction of adiabatic flame temperatures. We couple this with a model of heat transfer that includes convection, conduction as well as both radiative cooling and heating. This facilitates among other things ignition at a distance without heating up the intermediate air. We model the combustion as infinitely fast chemistry and couple this with the thin flame model, spatially varying laminar burning velocities based on local species and empirical measurements, physically validated soot formation and oxidation as well as water vapor production and condensation. We implement this on adaptive octree-like grids with collocated state variables, a new SBDF2-derived semi-Lagrangian time integrator for velocity, and a multigrid scheme used for multiple solver components. In combination, these models enable us to simulate deflagration phenomena ranging from small scale premixed and diffusion flames to fireballs and subsonic explosions which we demonstrate by several examples. In addition, we validate several of the results based on reference footage and measurements and discuss the relation of prevalent heuristic techniques arising in visual effects production to some of the physics-based models we propose.

Research on New Media Content Production Based on Artificial Intelligence Technology

At present, the main application of artificial intelligence in the media content production industry is to greatly reduce the application threshold, to a certain extent, to enable media workers to collect data from the low-end and produce visualization works for media terminals free from repetitive labor. Such as visual effects production, special effects design, video editing, subtitles sorting, data collection and comparison, image-text audio-video conversion, host broadcasting, and press release writing, are now increasingly completed through artificial intelligence programs. The working procedures of media content production are becoming more and more automated and intelligent.

Lagrangian neural style transfer for fluids

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.

영화시각효과 프로젝트에서 팀 역량 강화를 위한 스크럼 방법론 적용

As the computer graphic technology has developed rapidly, the management of visual effects production has also changed. However, the insufficient rest and the inefficiency of communication have resulted in more pressure which would weaken the strength of the whole team. For searching the possible solution, this research has applied the SCRUM in VFX production and analyzed the impact of SCRUM for VFX project management. SCRUM was first used in the projects of software development, but now there are already many successful examples of introducing SCRUM into their facilities in various fields. This paper has used SCRUM in the experimental group and present methodology in VFX project management in the control group for the same project. Based on the analysis of the questionnaire investigation from both group with using t-test for data analysis, it has confirmed the credibility of the questions in the questionnaire index as α > 0.72. With the result of analysis based on the corresponding samples of the t-test, it shows the diversity of SCRUM for project management, and the convenience of communication within the team can enhance the team strength. Follow-up research will attend to provide more suggestions for applying SCRUM in other areas in project management.

(Post)Production: Classifications and Infrastructures of Digital Visual Effects

This article historicizes the categorization of post-production work, specifically that of visual effects, as technical processes and “post” production in large-scale cinema production. It analyzes 1980s deregulations and the successive vertical integration strategies performed by studios to increase their control over distribution. The economic model of the contemporary blockbuster built upon concentrated studio control to redistribute the production of spectacle away from high-cost “creative” labor and into an expansive infrastructure of visual effects production that was more easily controllable and exploitable for central profit. An examination of visual effects classifications in the recent criticism on blockbusters by Kristen Whissel and Sean Cubitt will suggest that while visual effects function as primary components of textual design, we need to reconfigure how we describe this central component of filmmaking to shift the interests of its underlying infrastructure away from systemic profit and back to the human worker.

Synthesizing waves from animated height fields

Computer animated ocean waves for feature films are typically carefully choreographed to match the vision of the director and to support the telling of the story. The rough shape of these waves is established in the previsualization (previs) stage, where artists use a variety of modeling tools with fast feedback to obtain the desired look. This poses a challenge to the effects artists who must subsequently match the locked-down look of the previs waves with high-quality simulated or synthesized waves, adding the detail necessary for the final shot. We propose a set of automated techniques for synthesizing Fourier-based ocean waves that match a previs input, allowing artists to quickly enhance the input wave animation with additional higher-frequency detail that moves consistently with the coarse waves, tweak the wave shapes to flatten troughs and sharpen peaks if desired (as is characteristic of deep water waves), and compute a physically reasonable velocity field of the water analytically. These properties are demonstrated with several examples, including a previs scene from a visual effects production environment.

Organizational Creativity in Heterarchies: The Case of VFX Production

The aim of this paper is to portray organizational creativity as embedded in heterarchies rather than hierarchies or homoarchies. By drawing upon the case of visual effects (VFX) production, we demonstrate how heterarchies with multilayered, overlapping and incongruent organizational forms constitute a potential for organizational creativity that gets activated through a particular institutional arrangement of diversity. The article shows that analytically focusing on the properties of heterarchies can be a fruitful way to conceptualize context complexity as a resource rather than a barrier for organizational creativity.

Toward a theory of managing creativity-intensive processes: a creative industries study

This paper reports the results of an exploratory, theory-building study on the impact of creativity on business processes, their management, and the use of information technology (IT) in particular. The empirical evidence was derived from organizations within the creative industries, specifically film and visual effects (VFX) production. An adapted grounded theory approach was employed in order to analyze the data. The study identifies the dynamics of business processes that can be described as highly dependent on creativity, intensively involving the client, complex, and interdependent. It explains the processes' organizational context as well as strategies and IT systems that organizations use in order to manage these processes. The study suggests that creativity-intensive processes are characterized by high levels of uncertainty with regard to outcome, process structure, and required resources. Creative organizations pursue both creative and operational process performance while simultaneously mitigating creative and operational risk.